© 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. 29277
    Prev
    Next
    INDEX
    Explanations

    length of

    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°ģæĺ¯
    -0.07
    kaan
    -0.07
    édé
    -0.07
    rox
    -0.07
    anj
    -0.06
    ãģĭãģķ
    -0.06
    è¾
    -0.06
    aviolet
    -0.06
     Borsa
    -0.06
    $$$
    -0.06
    POSITIVE LOGITS
    æľĢå¤ļ
    0.16
    çļĦæľĢ大
    0.14
     possible
    0.13
    éĥ½æľīåı¯èĥ½
    0.13
     possibility
    0.13
     possibilities
    0.12
     getMax
    0.12
    æľīåı¯èĥ½
    0.12
     maximum
    0.12
    åı¯èĥ½åĩºçİ°
    0.12
    Activations Density 0.112%

    No Known Activations