© 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. 43819
    Prev
    Next
    INDEX
    Explanations

    the LICENSE

    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
    allon
    -0.07
    ities
    -0.07
    ully
    -0.07
    agia
    -0.07
    åºŀ
    -0.07
    æĸĩ广
    -0.07
    _RESPONSE
    -0.06
    mlin
    -0.06
    çĻ¾èĬ±
    -0.06
    ips
    -0.06
    POSITIVE LOGITS
    itchens
    0.08
    cion
    0.08
    åĽ½æĹĹ
    0.07
    念
    0.07
     balan
    0.07
    ssa
    0.07
    oras
    0.07
    åľ
    0.07
    åĽ½éĺ²éĥ¨
    0.07
    autiful
    0.07
    Activations Density 0.256%

    No Known Activations