Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 1839
    Prev
    Next
    INDEX
    Explanations

    Auto repairs and costs

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    楚
    -0.07
    닠
    -0.07
    鲉
    -0.06
    dc
    -0.06
    бар
    -0.06
     yardı
    -0.06
     Say
    -0.06
    计量
    -0.06
    迢
    -0.06
    ⼯
    -0.06
    POSITIVE LOGITS
    𦝼
    0.07
     guests
    0.07
    mPid
    0.07
    breadcrumbs
    0.07
     Couples
    0.07
     bored
    0.07
    ">';
    ↵
    0.07
    anders
    0.07
     уверен
    0.06
     elders
    0.06
    Activations Density 0.047%

    No Known Activations