© 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. 25294
    Prev
    Next
    INDEX
    Explanations

    and sketch

    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
    ibal
    -0.08
    첨
    -0.08
    æĮĿ
    -0.08
    endere
    -0.08
    ijIJ
    -0.07
    quate
    -0.07
    abilmente
    -0.07
    entimes
    -0.07
    roup
    -0.07
    práv
    -0.07
    POSITIVE LOGITS
    以åıĬå¦Ĥä½ķ
    0.08
    以åıĬåľ¨
    0.07
    并举
    0.07
    еÑĩÑĮ
    0.07
    并请
    0.06
    äºĮæĺ¯
    0.06
    loe
    0.06
    解æĥij
    0.06
     converse
    0.06
    »
    0.06
    Activations Density 0.112%

    No Known Activations