© 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. 7794
    Prev
    Next
    INDEX
    Explanations

    cut

    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
    åı«ä»Ģä¹Ī
    -0.09
    allah
    -0.08
    øy
    -0.07
    itect
    -0.07
    ammel
    -0.07
    è¿ĩä¸įåİ»
    -0.07
    inters
    -0.07
    ÑĢид
    -0.07
    estring
    -0.07
    /md
    -0.07
    POSITIVE LOGITS
    åĴĮæıIJé«ĺ
    0.07
    åĴĮæĿİ
    0.07
    åĬłæĭ¿å¤§
    0.07
    رة
    0.06
    apol
    0.06
    èĩªçĶ±
    0.06
    esch
    0.06
    çĶ¨æīĭæĮĩ
    0.06
    CALE
    0.06
     Calder
    0.06
    Activations Density 0.175%

    No Known Activations