© 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. 10158
    Prev
    Next
    INDEX
    Explanations

    hyphenated or bracketed compound words

    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
    uh
    -0.07
    boa
    -0.07
    usch
    -0.07
    Ùıد
    -0.06
    ous
    -0.06
    ulan
    -0.06
    å±±ä¹ĭ
    -0.06
    æľ¬ç«ĻæīĢæľī
    -0.06
    ange
    -0.06
    cho
    -0.06
    POSITIVE LOGITS
    enhagen
    0.08
    åħ¸
    0.07
    è¯ij为
    0.07
    ernos
    0.07
    geme
    0.07
    ìĸ´ì§Ħ
    0.07
    à¹ģà¸Ľà¸¥
    0.07
    ç¿»äºĨ
    0.06
    arly
    0.06
    gup
    0.06
    Activations Density 0.015%

    No Known Activations