© 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. 64587
    Prev
    Next
    INDEX
    Explanations

    short story

    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
    æī¿
    -0.08
     Grosso
    -0.07
    ontre
    -0.06
    ηÏģε
    -0.06
    帮åĬ©çļĦ人
    -0.06
    ÑĢаÑĤа
    -0.06
    çķĻå¿ĥ
    -0.06
    arshal
    -0.06
    OCUS
    -0.06
    æ¼ĶåĶ±
    -0.06
    POSITIVE LOGITS
    çe
    0.08
    ä¸įéķ¿
    0.08
    ÑĥÑĤÑĮ
    0.07
    irth
    0.07
    ìĩł
    0.07
    æ¸Ī
    0.07
    ç®ķ
    0.07
    aniel
    0.07
    ragen
    0.07
    çĻ½è¡Ģ
    0.07
    Activations Density 0.002%

    No Known Activations