© 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. 41533
    Prev
    Next
    INDEX
    Explanations

    following certain tokens

    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
    enk
    -0.06
    icemail
    -0.06
    .qq
    -0.06
     ActiveSupport
    -0.06
    ;text
    -0.06
    irk
    -0.05
    /kernel
    -0.05
     Indirizzo
    -0.05
    ×ĺר
    -0.05
     ÑĤоÑĢ
    -0.05
    POSITIVE LOGITS
     `
    0.10
    åIJį为
    0.09
    ãĢĮ
    0.08
    ãĢĬ
    0.08
    orough
    0.08
     '
    0.08
     `_
    0.08
     impro
    0.08
    ester
    0.08
     '__
    0.07
    Activations Density 0.508%

    No Known Activations