© 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. 15-RESID-POST-AA
    6. 13319
    Prev
    Next
    INDEX
    Explanations

    loss

    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
    "a
    -0.08
    ={{↵
    -0.07
     שלו
    -0.07
    嗓子
    -0.07
    黑恶势力
    -0.07
     التط
    -0.07
     Prince
    -0.07
     Wanna
    -0.07
    岛上
    -0.07
    .scale
    -0.07
    POSITIVE LOGITS
     heavier
    0.07
     Fairfax
    0.07
    CLA
    0.06
    夯实
    0.06
    .reader
    0.06
    (up
    0.06
    Flat
    0.06
     defeated
    0.06
    lug
    0.06
     secretive
    0.06
    Activations Density 0.045%

    No Known Activations