© 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. 32778
    Prev
    Next
    INDEX
    Explanations

    thought process

    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
    лÑıн
    -0.09
     Mediterran
    -0.08
    ÑĢек
    -0.08
    ắc
    -0.08
    elter
    -0.08
    embra
    -0.08
    entrum
    -0.07
    enis
    -0.07
    åį¡æĭī
    -0.07
    ëĤŃ
    -0.07
    POSITIVE LOGITS
    åİĨç¨ĭ
    0.07
    anta
    0.07
    éªļ
    0.07
     comp
    0.07
    è¿ĩç¨ĭ
    0.07
    ç¬Ķè®°
    0.06
     behind
    0.06
    ilig
    0.06
    æŃ·ç¨ĭ
    0.06
     BIM
    0.06
    Activations Density 0.005%

    No Known Activations