© 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. 20262
    Prev
    Next
    INDEX
    Explanations

    http:://

    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
    uo
    -0.07
    ille
    -0.07
    漪
    -0.07
    ora
    -0.07
    ä¸įå¼Ģ
    -0.06
    ä¸įåħ¥
    -0.06
     Massimo
    -0.06
    åįģ
    -0.06
    ck
    -0.06
    pf
    -0.06
    POSITIVE LOGITS
    以ä¸ĭç®Ģ称
    0.09
    éen
    0.08
    åħ¶çī¹å¾ģ
    0.08
    å½ĵä¹ĭæĹłæĦ§
    0.08
    èĩªå·±çļĦèĥ½åĬĽ
    0.07
    <?,
    0.07
    QUIRES
    0.07
    itized
    0.07
    åĪ«åIJį
    0.07
     ìĦ¤
    0.07
    Activations Density 0.088%

    No Known Activations