© 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. 62220
    Prev
    Next
    INDEX
    Explanations

    read more / continue reading

    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
    K
    -0.07
    æŀĹ
    -0.06
    xt
    -0.06
    oram
    -0.06
    M
    -0.06
    (
    -0.06
    x
    -0.06
    S
    -0.06
    X
    -0.05
     (
    -0.05
    POSITIVE LOGITS
    年建éĢł
    0.09
    ç«Ļç«Ļ
    0.08
    aeper
    0.08
    tep
    0.08
    DRV
    0.08
    ält
    0.08
    áŀİ
    0.08
    å¤§åĽ¾
    0.08
    &_
    0.08
     *(*
    0.08
    Activations Density 0.032%

    No Known Activations