© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 116725
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    .ob
    -0.07
    .role
    -0.07
    .Des
    -0.07
    }_${
    -0.07
     kit
    -0.06
    獲
    -0.06
    ⇔
    -0.06
    baru
    -0.06
     citizen
    -0.06
    /apt
    -0.06
    POSITIVE LOGITS
     منها
    0.08
    rega
    0.08
    ER
    0.07
    UMMY
    0.07
    _proto
    0.07
    _SAVE
    0.07
     CATEGORY
    0.07
    (pg
    0.07
     Strange
    0.07
     ER
    0.07
    Activations Density 0.036%

    No Known Activations