© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10803
    Prev
    Next
    INDEX
    Explanations

    colons and numbers

    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
    ingo
    -0.07
    QRS
    -0.07
    ub
    -0.06
    Ùİاد
    -0.06
    test
    -0.06
    a
    -0.06
    gend
    -0.06
    ahir
    -0.06
    ...
    -0.06
    æİ¢
    -0.06
    POSITIVE LOGITS
    errer
    0.08
     Ðķги
    0.08
    anship
    0.08
    accio
    0.08
    åı¯äº«
    0.08
    纾
    0.08
    plib
    0.08
    第ä¸īå±Ĭ
    0.07
    第åħŃå±Ĭ
    0.07
    æŀ¶
    0.07
    Activations Density 0.003%

    No Known Activations