© 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. 4264
    Prev
    Next
    INDEX
    Explanations

    gradients and order

    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
    æĿ¥ä¿¡
    -0.08
    ahme
    -0.07
    å±ł
    -0.07
    两æĿ¡
    -0.07
    ç©¿æ¢Ń
    -0.07
    涯
    -0.07
    æį¢æ°Ķ
    -0.07
    esis
    -0.07
    éĿłå·¦
    -0.07
    åŃ¤å²Ľ
    -0.07
    POSITIVE LOGITS
     asym
    0.08
    ä¸į对称
    0.07
     distort
    0.07
    åħŃ级
    0.07
    对称
    0.07
     distortion
    0.07
    ghan
    0.07
     wür
    0.07
    aad
    0.07
    å¹¼æķĻ
    0.07
    Activations Density 0.010%

    No Known Activations