© 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. 45138
    Prev
    Next
    INDEX
    Explanations

    investigation and determination

    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
    itters
    -0.10
    itter
    -0.08
    ĶĦ
    -0.07
    Unchecked
    -0.07
     Marr
    -0.07
    arty
    -0.07
     Mans
    -0.07
    _LS
    -0.07
    è¿Ľè¡Įæ£Ģæµĭ
    -0.07
    æ¯
    -0.07
    POSITIVE LOGITS
    以确å®ļ
    0.12
    åĨ³å®ļæĺ¯åIJ¦
    0.11
    å¾Ĺåĩºç»ĵ论
    0.11
    å¾ĹåĩºçļĦ
    0.10
    å¾Ĺåĩº
    0.10
    åıijçİ°æľī
    0.10
    ç¡®å®ļ
    0.09
    åĨ³å®ļ
    0.09
    æī¾åĩº
    0.09
     hasilnya
    0.09
    Activations Density 0.288%

    No Known Activations