© 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. 31850
    Prev
    Next
    INDEX
    Explanations

    void followed by method names

    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
     cor
    -0.07
    ancar
    -0.06
    让人è§īå¾Ĺ
    -0.06
    agos
    -0.06
    eyer
    -0.06
    çĵ¦å°Ķ
    -0.06
    对大家
    -0.06
    arian
    -0.06
    .lib
    -0.06
    çij
    -0.06
    POSITIVE LOGITS
    ä¿Ĺ
    0.08
    æľĢæĸ°æĽ´æĸ°
    0.08
    åıªå¾Ĺ
    0.08
     poda
    0.07
    izie
    0.07
    rades
    0.07
    lesi
    0.07
    eneur
    0.07
    иÑĤа
    0.07
    bahan
    0.07
    Activations Density 0.146%

    No Known Activations