© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63083
    Prev
    Next
    INDEX
    Explanations

    online services

    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
     Ñģобой
    -0.10
    ancis
    -0.09
    Ĺ
    -0.09
    oule
    -0.08
    chen
    -0.08
    malink
    -0.08
    ÏģαÏĢε
    -0.08
    æīĢåľ¨
    -0.08
    çIJĨå·¥åѦéĻ¢
    -0.08
    Ñĩи
    -0.08
    POSITIVE LOGITS
    /off
    0.11
    uropa
    0.08
    /up
    0.08
    entifier
    0.08
    idad
    0.08
    arity
    0.08
    ehme
    0.08
    thing
    0.07
    /out
    0.07
    stitut
    0.07
    Activations Density 0.041%

    No Known Activations