© 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. 29130
    Prev
    Next
    INDEX
    Explanations

    0.00 or 0.x

    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
    bsites
    -0.09
    .djang
    -0.08
    ä¹³ç³ĸ
    -0.08
    缸åħ³æݨèįIJ
    -0.08
    igny
    -0.07
    æĭīæī¯
    -0.07
    онеÑĨ
    -0.07
    иÑģло
    -0.07
    å¼ķçĶ¨æĹ¥æľŁ
    -0.07
    .squeeze
    -0.07
    POSITIVE LOGITS
    ailer
    0.07
     Tres
    0.06
    lsi
    0.06
    eph
    0.06
    بÙĥ
    0.06
    驹
    0.06
    _percentage
    0.06
    èĢ³æľµ
    0.06
    åıį
    0.06
    éĢļè¿ĩå¼Ģå±ķ
    0.06
    Activations Density 0.018%

    No Known Activations