© 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. 33558
    Prev
    Next
    INDEX
    Explanations

    to reorder, iterate, check, inspect

    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
    .done
    -0.08
    oref
    -0.07
    ìĿ´ëŀĢ
    -0.07
    æīĵå®Į
    -0.07
    meer
    -0.07
    åģļå®Į
    -0.07
    以åIJİåĨį
    -0.07
     beaten
    -0.07
    åIJĥå®Į
    -0.07
    spr
    -0.07
    POSITIVE LOGITS
    ห
    0.07
     mascul
    0.07
     cref
    0.07
    ((*
    0.06
    çĪ±ä¸į
    0.06
    ej
    0.06
    cher
    0.06
     deepest
    0.06
    moz
    0.06
    esima
    0.06
    Activations Density 0.049%

    No Known Activations