© 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. 14470
    Prev
    Next
    INDEX
    Explanations

    correction procedure

    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
    Reuse
    -0.07
    ç·Ĵ
    -0.07
    å¢ŀå¤ļ
    -0.07
    herit
    -0.07
    éĥ¨ç½²
    -0.07
     glGen
    -0.07
    解åĨ³éĹ®é¢ĺçļĦ
    -0.07
    onse
    -0.07
    ogl
    -0.07
    <|box_end|>
    -0.07
    POSITIVE LOGITS
     correction
    0.15
     corrections
    0.13
    æł¡æŃ£
    0.13
     Correction
    0.13
    Correction
    0.12
    çºłæŃ£
    0.12
     Corrections
    0.12
     correcting
    0.12
    _correction
    0.10
    ä¿®æŃ£
    0.10
    Activations Density 0.012%

    No Known Activations