© 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. 47622
    Prev
    Next
    INDEX
    Explanations

    polynomials

    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
     fazla
    -0.07
    åĴ¸
    -0.07
     foreign
    -0.07
    æľīåĪ©
    -0.06
     favorable
    -0.06
    åĴ½åĸī
    -0.06
    ge
    -0.06
    çĤ¹å¤ļ
    -0.06
    两å¤Ħ
    -0.06
    çĪ¬åĿ¡
    -0.06
    POSITIVE LOGITS
    Mapped
    0.09
    tridges
    0.08
     Kis
    0.08
    .construct
    0.07
    .pol
    0.07
    ×Ļר×Ļ×Ŀ
    0.07
     strad
    0.07
    .standard
    0.07
     derivatives
    0.07
    -strokes
    0.07
    Activations Density 0.021%

    No Known Activations