© 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. 57987
    Prev
    Next
    INDEX
    Explanations

    discuss-list posting

    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
    è¿ľ
    -0.07
    ry
    -0.07
    ัà¹Īà¸ĩ
    -0.06
     harbor
    -0.06
    oler
    -0.06
     except
    -0.06
    åĽŃ
    -0.06
    éģł
    -0.06
    รร
    -0.06
    å¤Ħ
    -0.06
    POSITIVE LOGITS
    userinfo
    0.09
    ä¾ĽåºĶ产åĵģ
    0.08
    ç»ĻæĪijçķĻè¨Ģ
    0.08
    Ð¢Ðł
    0.07
    SETS
    0.07
    baum
    0.07
    Scheduler
    0.07
    ITED
    0.07
    HEET
    0.07
    Scores
    0.07
    Activations Density 0.001%

    No Known Activations