© 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. 39873
    Prev
    Next
    INDEX
    Explanations

    committing verifying, enough by, reminder of, comfortable discussing

    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
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.08
    ivée
    -0.08
    ãĥĥãĤ·
    -0.07
    enuous
    -0.07
    åħ¶æīĢ
    -0.07
    Âł
    -0.07
    verbatim
    -0.07
    erus
    -0.07
    sexual
    -0.07
    volver
    -0.07
    POSITIVE LOGITS
    °
    0.06
    γÏīν
    0.06
    缨
    0.06
    ç»ĵæŀĦç®Ģåįķ
    0.06
    æĬĢæľ¯æĶ¯æĮģ
    0.06
    ä¹Łå¿«
    0.06
    ç»ĵæŀĦ示æĦıåĽ¾
    0.06
    转载请
    0.06
    æŶéĹ´éĩĮ
    0.06
    /fast
    0.06
    Activations Density 0.116%

    No Known Activations