© 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. 12998
    Prev
    Next
    INDEX
    Explanations

    components or distinct parts

    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
     Platt
    -0.08
     appropriate
    -0.07
    untime
    -0.07
    appropriate
    -0.07
    attu
    -0.06
    å¦Ĥæŀľæ²¡æľī
    -0.06
    ä¸įèĩ³äºİ
    -0.06
    chosen
    -0.06
     appropri
    -0.06
    ho
    -0.06
    POSITIVE LOGITS
     mysterious
    0.12
     unnamed
    0.11
     distinct
    0.10
     unidentified
    0.10
    distinct
    0.09
     elusive
    0.09
    ç¥ŀç§ĺçļĦ
    0.09
    çļĦåıijçİ°
    0.09
    åıijçİ°åľ¨
    0.09
     coinc
    0.09
    Activations Density 0.662%

    No Known Activations