© 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. 27570
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
     vast
    -0.08
    ctica
    -0.08
     vasta
    -0.08
     varietÃł
    -0.08
    lemen
    -0.08
     vues
    -0.07
    relude
    -0.07
    è´µå·ŀ
    -0.07
    veu
    -0.07
    vester
    -0.07
    POSITIVE LOGITS
    engeance
    0.12
    IRTUAL
    0.10
    новÑĮ
    0.10
    ERTICAL
    0.10
    oodoo
    0.10
    quez
    0.10
    Ñģпомина
    0.09
    ždy
    0.09
    ichni
    0.09
    ritable
    0.09
    Activations Density 0.207%

    No Known Activations