© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15113
    Prev
    Next
    INDEX
    Explanations

    rev

    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
    èĩ
    -0.07
    SENT
    -0.06
    åľ¨æŀĹ
    -0.06
    æŀĹ
    -0.06
    afia
    -0.06
    uation
    -0.06
    ç»ı纪åħ¬åı¸
    -0.06
    好æĦŁ
    -0.06
    acher
    -0.06
    æ¦ľ
    -0.06
    POSITIVE LOGITS
     reversed
    0.08
    reverse
    0.08
    rev
    0.07
    礼æĭľ
    0.07
    .Reverse
    0.07
    åıį
    0.07
    rel
    0.07
    åijĹ
    0.07
     sign
    0.07
    olved
    0.07
    Activations Density 0.031%

    No Known Activations