© 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. 25661
    Prev
    Next
    INDEX
    Explanations

    given / assuming that

    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
     Consort
    -0.07
    er
    -0.07
     surtout
    -0.07
    ä½ķçŃī
    -0.07
    usted
    -0.07
    æİ¥çĿĢ
    -0.06
    åĽŀæķ°
    -0.06
     others
    -0.06
    lo
    -0.06
    @if
    -0.06
    POSITIVE LOGITS
    dden
    0.08
    以ä¸ĭæĿ¡ä»¶
    0.07
     Sole
    0.07
    annie
    0.07
    icher
    0.07
    guer
    0.07
    "](
    0.07
    =utf
    0.07
    ikker
    0.07
    atamente
    0.06
    Activations Density 0.058%

    No Known Activations