© 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. 20154
    Prev
    Next
    INDEX
    Explanations

    ave

    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
    נג
    -0.07
    市场竞争
    -0.07
    网友
    -0.07
    submit
    -0.07
    朋友
    -0.07
    主体责任
    -0.07
    jp
    -0.07
    信息化
    -0.07
    неж
    -0.07
    jr
    -0.07
    POSITIVE LOGITS
    ATAR
    0.08
    fixed
    0.07
    UDA
    0.07
    ]"↵
    0.07
    _low
    0.07
    _MARGIN
    0.07
    需要
    0.07
     Та
    0.07
     دائما
    0.07
     DEV
    0.06
    Activations Density 0.002%

    No Known Activations