© 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. 55583
    Prev
    Next
    INDEX
    Explanations

    journal citations and names

    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
    éĽ¾
    -0.07
    cue
    -0.06
    sbin
    -0.06
    çĨŁ
    -0.06
    æĵį
    -0.06
    ä¹İ
    -0.06
    fo
    -0.06
    åħĪåľ¨
    -0.06
    egin
    -0.06
    take
    -0.06
    POSITIVE LOGITS
    illot
    0.08
    enius
    0.07
    åĽ½åľŁ
    0.07
    reden
    0.07
    alp
    0.07
    uhl
    0.07
     RELA
    0.07
    esco
    0.07
    æĸ°åįİ社
    0.07
    zaak
    0.07
    Activations Density 0.013%

    No Known Activations