© 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. 8763
    Prev
    Next
    INDEX
    Explanations

    code assignments and declarations

    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
    à¸ĩ
    -0.08
    à¸ķà¸Ļ
    -0.08
    ongs
    -0.07
    ç»Īå°Ĩ
    -0.07
    nero
    -0.07
    iar
    -0.07
    aggio
    -0.07
    %-
    -0.07
    äºİæѤ
    -0.07
    ner
    -0.07
    POSITIVE LOGITS
    _cast
    0.07
    omag
    0.07
    è¯Ī
    0.07
    essant
    0.06
     trâ
    0.06
    æĪĬ
    0.06
    çĽĪ
    0.06
    ank
    0.06
    CHAT
    0.06
    ÄĽn
    0.06
    Activations Density 0.016%

    No Known Activations