© 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. 63550
    Prev
    Next
    INDEX
    Explanations

    option selections

    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
    igió
    -0.08
    并ä¸į代表
    -0.08
    äºİä¸ĸ
    -0.07
    ç»ıæµİè´¸æĺĵ
    -0.07
    wad
    -0.07
    hent
    -0.07
    åĿĹ
    -0.06
    çĿ¡
    -0.06
    ÐĴÐĶ
    -0.06
    OT
    -0.06
    POSITIVE LOGITS
    æŃ£ç¢º
    0.07
    adh
    0.07
    rones
    0.07
    vore
    0.07
    ä¸Ģãģ¤
    0.07
    spur
    0.07
    èĸĩ
    0.07
    å°ijèµ°
    0.07
    ugn
    0.06
    Setter
    0.06
    Activations Density 0.009%

    No Known Activations