Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87118
    Prev
    Next
    INDEX
    Explanations

    mist

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HG
    -0.08
    发力
    -0.07
    esthetic
    -0.07
    া�
    -0.07
    CCI
    -0.07
    :hidden
    -0.07
    аг
    -0.07
    陶
    -0.07
    	Check
    -0.07
    구
    -0.07
    POSITIVE LOGITS
    벰
    0.08
     privile
    0.07
    overwrite
    0.07
    ië
    0.07
     Ağust
    0.07
     Orwell
    0.07
    前途
    0.06
    .emp
    0.06
     userService
    0.06
     democr
    0.06
    Activations Density 0.004%

    No Known Activations