© 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. 61085
    Prev
    Next
    INDEX
    Explanations

    second part or second half

    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
     Exhib
    -0.06
    ç»ķ
    -0.06
    æĮ¤åĩº
    -0.06
    åĽłä¸ºè¿Ļ
    -0.06
    irmi
    -0.06
    irmed
    -0.06
    ä»Ģä¹Īéĥ½æ²¡æľī
    -0.06
    _ie
    -0.05
    èħĭ
    -0.05
    usted
    -0.05
    POSITIVE LOGITS
    è°ĥæŁ¥åıijçİ°
    0.08
    åĪĻå°Ĩ
    0.08
    åĪĻ以
    0.08
    åĪĻåľ¨
    0.08
    plib
    0.08
    ãĥĩãĥª
    0.08
    pherd
    0.08
    åĪĻä¼ļ
    0.08
    oso
    0.08
    akers
    0.07
    Activations Density 0.019%

    No Known Activations