© 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. 3221
    Prev
    Next
    INDEX
    Explanations

    code, answer, or list

    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
    ä¸ĢçĤ¹åĦ¿
    -0.08
    wahl
    -0.08
    æī©å±ķèµĦæĸĻ
    -0.08
    ãģįãģª
    -0.08
    .leading
    -0.07
    னà¯įà®±
    -0.07
    çĤİçĥŃçļĦ
    -0.07
    æĽ¿å°¼
    -0.07
    janya
    -0.07
    enga
    -0.07
    POSITIVE LOGITS
     or
    0.09
     relative
    0.07
    æĪĸå¤ļ
    0.07
    æĢ§æĪĸ
    0.07
     somehow
    0.07
    à¹īาà¸ĩ
    0.07
    Relative
    0.07
    anz
    0.07
    osity
    0.07
    è§ģ她
    0.06
    Activations Density 0.006%

    No Known Activations