© 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. 47260
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    infeld
    -0.07
    loff
    -0.06
    ีà¸ģ
    -0.06
    ifte
    -0.06
    áh
    -0.06
    æľīçĽĬ
    -0.06
    éch
    -0.06
    &A
    -0.06
    æ±IJ
    -0.06
    iew
    -0.06
    POSITIVE LOGITS
    å¤§ä½ľæĪĺ
    0.08
    åIJĽçļĦ
    0.08
    ä¸Ģè¯ķ
    0.07
    åı¯æ¢¦
    0.07
    estellt
    0.07
    éģĩè§ģä½ł
    0.07
    åħ¨éĥ¨æ¥¼å±Ĥ
    0.07
    vaard
    0.07
    reek
    0.07
    è·¯éĢı
    0.07
    Activations Density 0.001%

    No Known Activations