© 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. 10313
    Prev
    Next
    INDEX
    Explanations

    tend toward

    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
    缸è¾ħ缸æĪIJ
    -0.08
     flagr
    -0.08
    ìĪŃ
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    تØŃ
    -0.08
    bie
    -0.07
    ombat
    -0.07
    hips
    -0.07
    EEK
    -0.07
    chestra
    -0.07
    POSITIVE LOGITS
     to
    0.10
    entially
    0.09
    weise
    0.09
    emente
    0.09
     toward
    0.08
     towards
    0.08
    åĪ°çļĦ
    0.07
    uate
    0.07
    ancy
    0.07
    antly
    0.07
    Activations Density 0.018%

    No Known Activations