© 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. 48936
    Prev
    Next
    INDEX
    Explanations

    derived dimension.hpp

    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
    Ñĥз
    -0.08
    means
    -0.07
    주ê°Ħ
    -0.07
    æ¤Ĵ
    -0.07
    åıªåī©
    -0.07
    ãĥ¼ãĥĪãĥ«
    -0.06
    terra
    -0.06
    太平æ´ĭ
    -0.06
     irm
    -0.06
    ayaan
    -0.06
    POSITIVE LOGITS
     arity
    0.07
    orne
    0.07
    ingo
    0.07
    ories
    0.07
    æĻ®éģįçļĦ
    0.07
    èĥ½åĬ¨æĢ§
    0.07
    æī¬
    0.07
    ÅĽl
    0.06
    aney
    0.06
    Carthy
    0.06
    Activations Density 0.002%

    No Known Activations