© 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. 45287
    Prev
    Next
    INDEX
    Explanations

    Bichel

    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
    -
    -0.07
    essin
    -0.07
    ve
    -0.06
    å¤įæĿĤ
    -0.06
    irit
    -0.06
    æĻĹ
    -0.06
    æīĢæľī
    -0.06
    IVO
    -0.06
    ãĥĬãĥĵ
    -0.06
    è¿ŀ
    -0.06
    POSITIVE LOGITS
    eih
    0.09
    áĥĺáĥ¢
    0.08
    ermen
    0.08
    gina
    0.08
    eteria
    0.08
    yczy
    0.07
    ãģ©ãĤĤ
    0.07
    chera
    0.07
    è´«åĽ°æĿij
    0.07
    ipun
    0.07
    Activations Density 0.001%

    No Known Activations