© 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. 25990
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    舆论
    -0.07
    уж
    -0.07
     zdjęcia
    -0.07
     reordered
    -0.07
    下载
    -0.07
     reput
    -0.06
    	scope
    -0.06
    办好
    -0.06
     đậu
    -0.06
    .On
    -0.06
    POSITIVE LOGITS
     Followers
    0.07
     generar
    0.07
    游击
    0.07
    每个
    0.06
     común
    0.06
    Cases
    0.06
    ий
    0.06
    灵动
    0.06
     principal
    0.06
    premium
    0.06
    Activations Density 0.152%

    No Known Activations