© 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. 7-RESID-POST-AA
    11. 39468
    Prev
    Next
    INDEX
    Explanations

    D-dimer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.07
    选择了
    -0.07
    足球
    -0.07
     일반
    -0.06
    	hs
    -0.06
    	Port
    -0.06
    u
    -0.06
    uyen
    -0.06
    kode
    -0.06
    舟山
    -0.06
    POSITIVE LOGITS
    섬
    0.08
     {}).
    0.06
    pretty
    0.06
    纂
    0.06
    �
    0.06
    뉍
    0.06
    เผยแพร
    0.06
    しゃ
    0.06
    _PRINTF
    0.06
    情形
    0.06
    Activations Density 0.001%

    No Known Activations