© 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. 86145
    Prev
    Next
    INDEX
    Explanations

    digital content and rights

    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
     aired
    -0.08
    .layoutControlItem
    -0.08
    irl
    -0.07
     tid
    -0.07
    ည
    -0.07
    strtotime
    -0.07
     Greenville
    -0.07
    �
    -0.07
     Weed
    -0.07
    灵活性
    -0.07
    POSITIVE LOGITS
    ҡ
    0.07
    מתי
    0.07
    defgroup
    0.07
    זול
    0.07
    ตร
    0.07
    ớ
    0.07
    .Asset
    0.07
    	Game
    0.06
     Jong
    0.06
     detector
    0.06
    Activations Density 0.058%

    No Known Activations