© 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. 51286
    Prev
    Next
    INDEX
    Explanations

    probability calculations from sets

    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
    伯æģ©
    -0.08
    onii
    -0.08
    acro
    -0.08
    croft
    -0.07
    icode
    -0.07
    borough
    -0.07
    emap
    -0.07
    holt
    -0.07
    erville
    -0.07
     muôn
    -0.07
    POSITIVE LOGITS
     ref
    0.07
    åŀ¦
    0.06
     B
    0.06
    èĤł
    0.06
     vs
    0.06
    _OK
    0.06
     Miss
    0.06
     reve
    0.06
     Ãģ
    0.06
    miss
    0.05
    Activations Density 0.006%

    No Known Activations