© 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. 2218
    Prev
    Next
    INDEX
    Explanations

    STEP SIDE, SVG IMAGES

    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
    ster
    -0.07
    loo
    -0.07
    ahoo
    -0.06
    è´º
    -0.06
    åŃ©åŃIJåĢij
    -0.06
    uen
    -0.06
    æĨ¬
    -0.06
    adura
    -0.06
    ureau
    -0.05
    å²Ĺ
    -0.05
    POSITIVE LOGITS
    icontrol
    0.08
    ä»Ģä¹Īéĥ½æ²¡æľī
    0.08
    expo
    0.07
    ixer
    0.07
    ä¸İåīį
    0.07
    -meta
    0.07
    å¾Ĺæīĭ
    0.07
    ertext
    0.07
    ORB
    0.07
    -await
    0.07
    Activations Density 0.003%

    No Known Activations