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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 72553
    Prev
    Next
    INDEX
    Explanations

    Code test suites

    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
    볶
    -0.08
    公务员
    -0.07
    结束
    -0.07
     semp
    -0.07
     pharmacy
    -0.07
    觖
    -0.07
    _RADIUS
    -0.07
    婆婆
    -0.07
    编号
    -0.06
    .weapon
    -0.06
    POSITIVE LOGITS
    转型发展
    0.08
     ROLE
    0.08
    ると
    0.07
     alternative
    0.07
    AMY
    0.07
    画像
    0.07
    能使
    0.07
    arie
    0.07
    Joint
    0.07
    stands
    0.07
    Activations Density 0.000%

    No Known Activations