© 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. 25969
    Prev
    Next
    INDEX
    Explanations

    actions and states

    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
    çļĦä¸ĢåĪĩéĥ½
    -0.10
    ÈĽine
    -0.10
    agher
    -0.09
    Å¡kai
    -0.09
    çŃīåįķä½į
    -0.09
    ówno
    -0.09
    ---</
    -0.08
    macher
    -0.08
    <|box_end|>
    -0.08
    imte
    -0.08
    POSITIVE LOGITS
    ä¸įåĪ°çļĦ
    0.09
    å·²ä¹ħçļĦ
    0.08
    ä¹ĭå¤Ħ
    0.08
    ÑģÑı
    0.08
    æĢ§çļĦ
    0.08
    åĪ°çļĦ
    0.08
    æĢ§
    0.08
    ä¸įå®ĮçļĦ
    0.08
    nam
    0.08
    åīĤ
    0.08
    Activations Density 0.007%

    No Known Activations