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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 31434
    Prev
    Next
    INDEX
    Explanations

    programming data

    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
    etCode
    -0.07
     express
    -0.07
    orre
    -0.07
    增量
    -0.07
    нибуд
    -0.07
    .power
    -0.07
    -radius
    -0.07
    歌唱
    -0.07
    מזג
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    (percent
    0.08
     Association
    0.07
    matchCondition
    0.07
    _ary
    0.07
    (Cs
    0.07
    ỷ
    0.07
     Globals
    0.07
    𝘰
    0.07
    万物
    0.07
    AI
    0.07
    Activations Density 0.069%

    No Known Activations