© 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. 16587
    Prev
    Next
    INDEX
    Explanations

    determination of

    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
    abay
    -0.08
    _static
    -0.07
    顺åħ¶èĩªçĦ¶
    -0.07
    åħ¬çĪµ
    -0.07
     artic
    -0.07
     tor
    -0.07
    çŃĭèĨľ
    -0.07
    ç¥ŀç»ıçĹĽ
    -0.07
     cushions
    -0.06
    åĬłæĭī
    -0.06
    POSITIVE LOGITS
     assay
    0.12
     detection
    0.11
    çļĦæ£Ģæµĭ
    0.11
     assays
    0.11
    æ£Ģæµĭ
    0.11
     adul
    0.11
    æµĭå®ļ
    0.11
    æ£Ģæµĭæĸ¹æ³ķ
    0.10
    å¾®éĩı
    0.10
     detecting
    0.10
    Activations Density 0.367%

    No Known Activations