© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17996
    Prev
    Next
    INDEX
    Explanations

    obtain/get

    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
    缸è¾ħ缸æĪIJ
    -0.12
    jenigen
    -0.11
    äºĭåįĬåĬŁåĢį
    -0.10
    åĬłæĭ¿å¤§
    -0.10
    ature
    -0.10
    ellaneous
    -0.09
    åĭĩå¾Ģ缴åīį
    -0.09
    ï¸İ
    -0.09
    odyn
    -0.09
    enticate
    -0.09
    POSITIVE LOGITS
    çļĦæĺ¯ä¸Ģ个
    0.10
    ÑģÑĮ
    0.10
    äºĨä¸Ģç§į
    0.09
    и
    0.08
    çļĦæĺ¯
    0.08
     volna
    0.07
    äºĨä¸Ģ
    0.07
    好å¤ĦçļĦ
    0.07
    çļĦæĺ¯ä»Ģä¹Ī
    0.07
    er
    0.07
    Activations Density 0.001%

    No Known Activations