© 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. 40980
    Prev
    Next
    INDEX
    Explanations

    see below or copyright notice

    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
    IBC
    -0.08
    Accessor
    -0.08
    ä¸įåĩı
    -0.07
    åĨħ容åĮħæĭ¬
    -0.07
    åĬŁèĥ½æĺ¯
    -0.07
    oret
    -0.06
     (;
    -0.06
    稿
    -0.06
    .design
    -0.06
    ظÙĩ
    -0.06
    POSITIVE LOGITS
    å°±çŁ¥éģĵäºĨ
    0.09
     below
    0.08
    below
    0.07
     abaixo
    0.07
    arth
    0.07
    髦
    0.07
    è§ģ
    0.07
    igation
    0.06
    vak
    0.06
    į°
    0.06
    Activations Density 0.296%

    No Known Activations