© 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. 12586
    Prev
    Next
    INDEX
    Explanations

    first post. I have. the same

    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
    ulina
    -0.07
     поÑģа
    -0.07
    astique
    -0.07
    uya
    -0.07
    -generic
    -0.07
     Curtis
    -0.07
    univers
    -0.07
     loc
    -0.07
    uars
    -0.06
    onga
    -0.06
    POSITIVE LOGITS
    缴æİ¥è¿Ľåħ¥
    0.09
    /releases
    0.07
    缴æݥ就
    0.07
    缴æİ¥åħ³ç³»åĪ°
    0.07
    èĩªçĦ¶èĢĮ
    0.07
    çIJ
    0.07
     langsung
    0.07
     instinct
    0.06
    æľ¬èº«å°±æĺ¯
    0.06
     raw
    0.06
    Activations Density 0.008%

    No Known Activations