© 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. 8063
    Prev
    Next
    INDEX
    Explanations

    `inner product contraction`

    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
    ç»Ħéķ¿
    -0.07
    åŃ°
    -0.07
    è¯ļå®ŀ
    -0.06
    otype
    -0.06
     autoc
    -0.06
    anch
    -0.06
    éĩįéĩı
    -0.06
    otin
    -0.06
    wt
    -0.06
     weight
    -0.06
    POSITIVE LOGITS
    ogat
    0.08
    åıĤä¸İçļĦ
    0.08
    ç¥ŀç»ı
    0.08
    æ¶Ī
    0.08
    rever
    0.08
    itazione
    0.07
    ieza
    0.07
    æ·±åĪ»åľ°
    0.07
    isle
    0.07
    lacht
    0.07
    Activations Density 0.001%

    No Known Activations