© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58821
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting

    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
     *(*
    -0.07
    ppo
    -0.07
     поп
    -0.07
    ¤íģ
    -0.07
    unst
    -0.07
    quiera
    -0.07
    engel
    -0.07
    emente
    -0.07
    ack
    -0.07
    trup
    -0.07
    POSITIVE LOGITS
    éĩıèĥ½
    0.07
    ÑĨеле
    0.06
    ilton
    0.06
    oten
    0.06
    çŀŃ
    0.06
    viar
    0.06
    人èĥ½
    0.06
    ษ
    0.06
    涣
    0.06
    apers
    0.06
    Activations Density 0.007%

    No Known Activations