© 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. 24733
    Prev
    Next
    INDEX
    Explanations

    directing action

    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
    èijĨ
    -0.08
    åĪļéľĢ
    -0.08
    éz
    -0.07
    ä¸Ģ线
    -0.06
    rine
    -0.06
    èĦijçŃĭ
    -0.06
    onav
    -0.06
    onge
    -0.06
    coh
    -0.06
    ä¾®
    -0.06
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģç§į
    0.09
    ¦
    0.08
    館
    0.07
    æľĪä¸Ĭ
    0.07
    LAY
    0.07
    drs
    0.07
    åı¯ä»¥æıIJä¾Ľ
    0.07
    ÑĥÑī
    0.07
    ä¸įä»ħåı¯ä»¥
    0.07
    åĥıåľ¨
    0.07
    Activations Density 0.637%

    No Known Activations