© 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. 50616
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and operators

    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
    æĸ°åĬłåĿ¡
    -0.09
    åĬłæĭ¿å¤§
    -0.08
     demais
    -0.06
    éĺ¿æĭī伯
    -0.06
    æ¯Ľæ³½ä¸ľ
    -0.06
    俱ä¹IJéĥ¨
    -0.06
     itself
    -0.05
    åħ·å¤ĩä¸Ģå®ļçļĦ
    -0.05
    pmat
    -0.05
    ixa
    -0.05
    POSITIVE LOGITS
    ousand
    0.08
    undred
    0.08
    <|box_end|>
    0.08
    ekk
    0.08
    onos
    0.08
    ÑģнÑĥÑİ
    0.07
    alda
    0.07
    amol
    0.07
    avais
    0.07
    ekyll
    0.07
    Activations Density 0.021%

    No Known Activations