© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21599
    Prev
    Next
    INDEX
    Explanations

    column, substrate, decision, view, menu, center, permissions

    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
    uha
    -0.07
    jør
    -0.07
    ä¹ĭä½ľ
    -0.07
    ìłķìĿĺ
    -0.07
    åħĢ
    -0.07
    ä¸İä¹ĭ
    -0.06
    (report
    -0.06
    @include
    -0.06
    åģļå¾ĹæĽ´å¥½
    -0.06
    ürg
    -0.06
    POSITIVE LOGITS
    ách
    0.07
    interop
    0.07
    teca
    0.07
    å·§
    0.06
    å·¥ä½ľä¸Ĭ
    0.06
    çĽ
    0.06
    unku
    0.06
    象æ£ĭ
    0.06
    á»ıng
    0.06
    Âł
    0.06
    Activations Density 0.853%

    No Known Activations