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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 129073
    Prev
    Next
    INDEX
    Explanations

    biometric data/image recognition

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .sn
    -0.08
    ventario
    -0.07
    主题活动
    -0.07
    食品安全
    -0.07
     favourable
    -0.07
    达到了
    -0.07
    statuses
    -0.07
     london
    -0.07
     hamburger
    -0.07
    江西省
    -0.07
    POSITIVE LOGITS
    咳
    0.07
    ไ
    0.07
    Gray
    0.06
    ellow
    0.06
    α
    0.06
     Operators
    0.06
    蕤
    0.06
    ἑ
    0.06
     demás
    0.06
    册
    0.06
    Activations Density 0.076%

    No Known Activations