© 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. 62387
    Prev
    Next
    INDEX
    Explanations

    debug statements and _client code

    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
    êu
    -0.08
    ifax
    -0.06
    ibus
    -0.06
    <|box_end|>
    -0.06
    _modules
    -0.06
    æĪĺ线
    -0.06
    еÑĢед
    -0.05
    play
    -0.05
    ÏĢο
    -0.05
    ä½ĻçĥŃ
    -0.05
    POSITIVE LOGITS
    æ§Ľ
    0.08
    esm
    0.08
    ä¸īå°º
    0.08
    dsm
    0.08
    lingen
    0.08
    orman
    0.07
    ä¸Ī
    0.07
    urable
    0.07
    ulet
    0.07
    浩çĦ¶
    0.07
    Activations Density 0.038%

    No Known Activations