© 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. 3781
    Prev
    Next
    INDEX
    Explanations

    years and paper identifiers

    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
    veld
    -0.08
    天éķ¿
    -0.08
    izr
    -0.07
    è²Ķ
    -0.07
    çļĦå°ıç¼ĸ
    -0.07
    ħ
    -0.07
    çĭ±
    -0.07
    andat
    -0.07
    ockets
    -0.07
    çıĤ
    -0.07
    POSITIVE LOGITS
    ä¸Ģæĸĩ
    0.08
    éĽªçIJĥ
    0.07
    éĻ°
    0.07
    æ§ĭ
    0.06
    bit
    0.06
    表éĿ¢ä¸Ĭ
    0.06
    eyer
    0.06
    çĻ½æĹ¥
    0.06
    å¤ĩæ¡Īåı·
    0.06
    ipur
    0.06
    Activations Density 0.260%

    No Known Activations