© 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. 64950
    Prev
    Next
    INDEX
    Explanations

    proofs and classes of complexity

    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
    ä¹ĭä¸ī
    -0.07
    åıĤä¸İæ´»åĬ¨
    -0.07
    åĪĿå§ĭ
    -0.07
    bersome
    -0.06
    zyd
    -0.06
     initial
    -0.06
    åħ±æľī
    -0.06
     neighbouring
    -0.06
    UNE
    -0.06
     initially
    -0.06
    POSITIVE LOGITS
    ouro
    0.08
    owe
    0.08
     vastly
    0.08
    对åIJĦç§į
    0.08
    outdir
    0.08
    çon
    0.08
     proofs
    0.08
    éĺ¶
    0.08
    åIJİæĦŁ
    0.07
     mildly
    0.07
    Activations Density 0.016%

    No Known Activations