© 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. 3911
    Prev
    Next
    INDEX
    Explanations

    string manipulation

    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
    ãģ£ãģįãĤĬ
    -0.11
    ÅĽwiÄĻ
    -0.09
    ussin
    -0.09
    ëģĶ
    -0.08
    iless
    -0.08
    ï¸İ
    -0.08
    stätten
    -0.08
    à¸Ļà¹Į
    -0.08
     Äijặn
    -0.08
    rlen
    -0.08
    POSITIVE LOGITS
    ategies
    0.10
    hood
    0.09
    à¹Īาย
    0.08
    à¸Ħà¹Į
    0.08
    .fromCharCode
    0.08
    ategic
    0.08
    .ascii
    0.07
    y
    0.07
    buf
    0.07
    è¾Ī
    0.07
    Activations Density 0.096%

    No Known Activations