© 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. 11193
    Prev
    Next
    INDEX
    Explanations

    anode cathode

    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
    æĭħ
    -0.07
    ithe
    -0.07
    lez
    -0.07
    ied
    -0.07
    ings
    -0.06
    ä¸İ设计
    -0.06
    outers
    -0.06
    缸è¾ħ缸æĪIJ
    -0.06
    ATIONS
    -0.06
    ations
    -0.06
    POSITIVE LOGITS
    ward
    0.09
    rons
    0.09
    esis
    0.08
    arca
    0.08
    avra
    0.08
    मार
    0.08
    ovac
    0.08
    -most
    0.08
    elic
    0.08
    å¨ĺå¨ĺ
    0.08
    Activations Density 0.012%

    No Known Activations