© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48050
    Prev
    Next
    INDEX
    Explanations

    git commit diffs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.08
    oles
    -0.07
    orent
    -0.06
    erma
    -0.06
    _abstract
    -0.06
    ç¬
    -0.06
    prs
    -0.06
    erre
    -0.06
    älter
    -0.06
    ç»ĵæŀĦç®Ģåįķ
    -0.06
    POSITIVE LOGITS
    ç½²
    0.09
    bti
    0.07
    bay
    0.07
    æľ¬æ¥¼
    0.07
    aday
    0.07
    мÑĭÑĪ
    0.07
     Blanc
    0.07
     dope
    0.07
    ยาย
    0.07
    NIL
    0.07
    Activations Density 0.004%

    No Known Activations