© 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. 40091
    Prev
    Next
    INDEX
    Explanations

    primary, normal, regular, acute, short-term

    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
    ogia
    -0.07
    åĤį
    -0.07
    ä¸Ģè§ī
    -0.07
    è·³
    -0.07
    æ·
    -0.07
    inker
    -0.07
    è¹Ī
    -0.07
     chal
    -0.07
    illy
    -0.07
    оÑģÑĥ
    -0.07
    POSITIVE LOGITS
    lay
    0.07
    éĺ¶æ®µçļĦ
    0.07
    CAM
    0.07
     stage
    0.07
     kin
    0.07
    baz
    0.07
    uC
    0.07
    åŁİ西
    0.07
    hoe
    0.06
    stage
    0.06
    Activations Density 0.526%

    No Known Activations