© 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. 3641
    Prev
    Next
    INDEX
    Explanations

    delivered by

    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
    åıªè¦ģæľī
    -0.07
     sır
    -0.07
    åħ¶èĩªçĦ¶
    -0.07
    æĪĸåħ¶
    -0.06
     ret
    -0.06
    ongan
    -0.06
    _BY
    -0.06
    ehen
    -0.06
     REFERENCES
    -0.06
    以åħ¶
    -0.06
    POSITIVE LOGITS
    anst
    0.07
     bás
    0.07
    诣
    0.07
    sier
    0.07
    Ñģпа
    0.07
    漪
    0.07
    çķ¢
    0.07
    kam
    0.07
    krim
    0.07
    bang
    0.06
    Activations Density 0.014%

    No Known Activations