© 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. 26062
    Prev
    Next
    INDEX
    Explanations

    how many are there

    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
    Ñijл
    -0.08
    lyn
    -0.08
    æĢİä¹Īçľĭ
    -0.08
    wers
    -0.07
    irut
    -0.07
    OrFail
    -0.07
    targets
    -0.07
    ÃŃta
    -0.07
    åĩ¡æĺ¯
    -0.07
    Exposed
    -0.07
    POSITIVE LOGITS
    UNUSED
    0.07
    habil
    0.06
     thá»į
    0.06
    dbl
    0.06
    [:
    0.06
    溶äºİ
    0.06
    IANO
    0.06
     total
    0.06
    çļĦ好æľĭåıĭ
    0.06
    DBG
    0.06
    Activations Density 0.012%

    No Known Activations