© 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. 11434
    Prev
    Next
    INDEX
    Explanations

    preliminary evidence or studies

    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
    ycz
    -0.08
     tue
    -0.07
    elib
    -0.07
    éŀŃ
    -0.07
    å¾Īæ¸ħæ¥ļ
    -0.07
    å±ħé«ĺä¸įä¸ĭ
    -0.07
    esub
    -0.07
    lesa
    -0.07
    olean
    -0.07
    uality
    -0.07
    POSITIVE LOGITS
    åĪĿæŃ¥
    0.16
    ëĤĺë§Ī
    0.13
     preliminary
    0.12
    éĽıå½¢
    0.11
     glimpse
    0.11
     tentative
    0.10
     Prel
    0.10
    端åĢª
    0.10
     hints
    0.10
    iminary
    0.09
    Activations Density 0.191%

    No Known Activations