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. 42288
    Prev
    Next
    INDEX
    Explanations

    ---

    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
    Actions
    -0.07
    <>();↵↵
    -0.07
    lined
    -0.07
    /cpp
    -0.06
     reflective
    -0.06
     legs
    -0.06
    Directed
    -0.06
    (),↵
    -0.06
    hiếu
    -0.06
    掛け
    -0.06
    POSITIVE LOGITS
    inar
    0.08
    fw
    0.08
    เทคน
    0.08
     melting
    0.07
     Beam
    0.07
    ating
    0.07
    酵
    0.07
    corp
    0.07
    被淘汰
    0.07
     Hour
    0.07
    Activations Density 0.004%

    No Known Activations