© 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. 1198
    Prev
    Next
    INDEX
    Explanations

    proposed solution format

    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
    çijŀæĭī
    -0.07
    çİĽçijĻ
    -0.07
    以å¾ħ
    -0.07
    acades
    -0.07
    essem
    -0.07
    åį³ä»¥
    -0.07
    åıĸåħ¶
    -0.07
    .TypeOf
    -0.07
    好ä¸į
    -0.07
    untime
    -0.07
    POSITIVE LOGITS
     purported
    0.09
     proposed
    0.09
     claimed
    0.08
     validated
    0.08
    claimed
    0.08
     allegedly
    0.08
     reportedly
    0.08
     verified
    0.08
    æŃ£ç¡®åľ°
    0.08
     alleged
    0.07
    Activations Density 0.021%

    No Known Activations