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. 19-RESID-POST-AA
    6. 36550
    Prev
    Next
    INDEX
    Explanations

    :

    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
    统筹推进
    -0.07
    INATION
    -0.07
    master
    -0.07
     Tháng
    -0.07
     persone
    -0.06
     describe
    -0.06
     Я
    -0.06
     ry
    -0.06
    倘
    -0.06
    _staff
    -0.06
    POSITIVE LOGITS
    _MSG
    0.07
    .apple
    0.06
    (tuple
    0.06
    _assignment
    0.06
     token
    0.06
     recl
    0.06
    /';↵
    0.06
    信贷
    0.06
     Vegan
    0.06
    itive
    0.06
    Activations Density 0.001%

    No Known Activations