© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 21146
    Prev
    Next
    INDEX
    Explanations

    network code

    np_max-act · gemini-2.0-flash

    descriptions or code related to TCP/IP socket networking and client–server connections across programming languages.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _SIG
    -0.07
    ✱
    -0.07
    滉
    -0.07
    IALIZ
    -0.07
     المسي
    -0.06
    מוז
    -0.06
    哚
    -0.06
    主演
    -0.06
    clazz
    -0.06
    坚实
    -0.06
    POSITIVE LOGITS
    couldn
    0.08
    )))↵↵
    0.07
    ++){
    0.07
    שמ
    0.07
    естеств
    0.07
    eras
    0.07
    tu
    0.06
    emergency
    0.06
    >t
    0.06
    )))))↵
    0.06
    Activations Density 0.029%

    No Known Activations