© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 75871
    Prev
    Next
    INDEX
    Explanations

    code data types

    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
    .Atomic
    -0.07
    滗
    -0.07
    氆
    -0.07
    得知
    -0.07
    ʶ
    -0.07
    CONDITION
    -0.07
    冉
    -0.06
     �
    -0.06
    掐
    -0.06
     iş
    -0.06
    POSITIVE LOGITS
    更多
    0.07
     '}↵
    0.07
    .addSubview
    0.07
     "}↵
    0.07
     ${↵
    0.07
    外科
    0.07
    زيارة
    0.07
    _BO
    0.07
    旗舰店
    0.07
     buckle
    0.07
    Activations Density 0.004%

    No Known Activations