© 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. 48992
    Prev
    Next
    INDEX
    Explanations

    final, overall goal

    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
    ess
    -0.06
    è¥Ħ
    -0.06
    _limits
    -0.06
    esser
    -0.06
    eso
    -0.06
    ean
    -0.06
    æĬ¢çľ¼
    -0.05
    ấn
    -0.05
    pr
    -0.05
     Fab
    -0.05
    POSITIVE LOGITS
    ì§Ģë§ī
    0.08
    éĻħ
    0.08
    xel
    0.08
    ä¹į
    0.08
    eil
    0.08
    à¤ļार
    0.08
    tep
    0.08
    ignan
    0.08
    /current
    0.08
    ovah
    0.08
    Activations Density 0.003%

    No Known Activations