© 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. 58353
    Prev
    Next
    INDEX
    Explanations

    medical or technical descriptions

    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
    reur
    -0.08
    åIJĮä¸Ĭ
    -0.07
    对ä¸Ĭè¿°
    -0.07
    UES
    -0.07
    kov
    -0.07
    ardi
    -0.07
    éģIJ
    -0.06
    éģĵåıĭ
    -0.06
    ottes
    -0.06
    éĥİ
    -0.06
    POSITIVE LOGITS
    chenk
    0.08
    _TD
    0.08
    ripper
    0.07
    edef
    0.07
    iona
    0.07
    AGR
    0.07
    caret
    0.07
    ~=
    0.07
    eted
    0.07
    è¡ħ
    0.07
    Activations Density 0.402%

    No Known Activations