© 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. 29177
    Prev
    Next
    INDEX
    Explanations

    multiplied or list 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
    绣
    -0.08
    滩
    -0.07
    讲究
    -0.07
    èĤ¯
    -0.07
    ike
    -0.07
    å¸ĥæĭī
    -0.07
    mati
    -0.07
    ç®Ĺæĺ¯
    -0.07
    jÄĻ
    -0.07
    .define
    -0.07
    POSITIVE LOGITS
     fucked
    0.07
     multiplied
    0.07
    è¹Ĥ
    0.07
    èĩªèº«çļĦ
    0.07
    æľ¬èº«çļĦ
    0.07
    ä¹ĺ以
    0.07
    awks
    0.06
    Minus
    0.06
     slightly
    0.06
     Howard
    0.06
    Activations Density 0.001%

    No Known Activations