© 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. 19-RESID-POST-AA
    11. 109572
    Prev
    Next
    INDEX
    Explanations

    gaining recognition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "http
    -0.08
    江苏
    -0.07
    есть
    -0.07
     Soy
    -0.07
    氚
    -0.07
    cow
    -0.07
    𝘸
    -0.07
    value
    -0.07
    =yes
    -0.07
    款
    -0.06
    POSITIVE LOGITS
    ✄
    0.07
    Inflater
    0.07
    StringRef
    0.07
     continual
    0.07
    undle
    0.07
    お勧
    0.07
    _TestCase
    0.07
    oster
    0.07
     depleted
    0.06
    _Instance
    0.06
    Activations Density 0.073%

    No Known Activations