© 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. 61197
    Prev
    Next
    INDEX
    Explanations

    issue or problem

    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
    olean
    -0.09
    ecker
    -0.08
    Qed
    -0.08
    /meta
    -0.08
    abda
    -0.08
    éns
    -0.08
    å¤ĸåĽ½è¯ŃåŃ¦æł¡
    -0.08
    ÑģÑĤÑĢо
    -0.08
    ooled
    -0.08
    plevel
    -0.08
    POSITIVE LOGITS
    ...
    0.07
    ï¼Ī
    0.07
    å®ľ
    0.06
    ...(
    0.06
    类似
    0.06
    kind
    0.06
    åĬĽ
    0.06
    jet
    0.06
     Matter
    0.06
    æŁIJç§į
    0.05
    Activations Density 0.001%

    No Known Activations