© 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. 43871
    Prev
    Next
    INDEX
    Explanations

    sabo, adjacent, cream, Dave, Lida

    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
    ίÏīν
    -0.07
    çŀ°
    -0.07
    æĭ¬
    -0.06
    occas
    -0.06
    åħī
    -0.06
    iative
    -0.06
    еÑģпе
    -0.06
    opan
    -0.06
    ITICAL
    -0.06
    dash
    -0.06
    POSITIVE LOGITS
    ament
    0.08
    voz
    0.07
    azzo
    0.07
    ç²
    0.07
    istr
    0.07
     Kou
    0.06
    amento
    0.06
    èĪįä¸įå¾Ĺ
    0.06
    Loc
    0.06
    pez
    0.06
    Activations Density 0.317%

    No Known Activations