© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14194
    Prev
    Next
    INDEX
    Explanations

    mathematical and code variables

    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
    çļĦ人æĿ¥è¯´
    -0.06
    Uns
    -0.06
    (/^\
    -0.06
     rense
    -0.06
    精彩åĨħ容
    -0.06
    èµ°éģį
    -0.06
     Antw
    -0.06
    ayne
    -0.06
    åħ«è¾¾
    -0.06
    zcze
    -0.06
    POSITIVE LOGITS
    omis
    0.08
    rau
    0.08
    ptest
    0.07
    åħ¶ä¸ŃæľĢ
    0.07
    å§Ķ
    0.07
    VID
    0.07
    udent
    0.07
     likewise
    0.07
    plen
    0.07
     **.**
    0.07
    Activations Density 0.019%

    No Known Activations