© 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. 27202
    Prev
    Next
    INDEX
    Explanations

    searching for specific formats

    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
    åľ°ä¸İ
    -0.09
    ä¸İ交æµģ
    -0.09
    æĺ¯ä¸Ģåľº
    -0.09
    èĥ½ä¸º
    -0.08
    åįĹèĩ³
    -0.08
    并åıijå¸ĥ
    -0.08
    åľ°çľĭçĿĢ
    -0.08
    åijĬè¯īäºĨ
    -0.08
    æĢ§ä¸İ
    -0.08
    .onStart
    -0.08
    POSITIVE LOGITS
    è¿Ľè¡Į
    0.14
    éĢ²è¡Į
    0.09
    设å¤ĩè¿Ľè¡Į
    0.09
    è¿Ľè¡Į交æĺĵ
    0.09
    è¿Ľè¡Įè¿ĩ
    0.08
    è¿Ľè¡Įæ²»çĸĹ
    0.08
    çŃīè¿Ľè¡Į
    0.07
    è¿Ľè¡Įæĵįä½ľ
    0.07
    以å¤ĸçļĦ
    0.07
    amed
    0.07
    Activations Density 0.034%

    No Known Activations