© 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. 51035
    Prev
    Next
    INDEX
    Explanations

    column delimiters or field names

    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
    ocoa
    -0.07
    å¹³æ»ij
    -0.07
    çĭ¬
    -0.06
    lagen
    -0.06
    enu
    -0.06
    lew
    -0.06
    eu
    -0.06
    rak
    -0.06
     اÙĦÙĤائÙħ
    -0.06
     tones
    -0.06
    POSITIVE LOGITS
    untung
    0.08
    ertz
    0.08
    ä¸ļçļĦ
    0.07
    èĦ±é¢ĸ
    0.07
    Å¡ÃŃ
    0.07
     Trojan
    0.07
    ä¸ŃåĮº
    0.07
    gne
    0.07
    髦
    0.07
    ä¸īçľģ
    0.07
    Activations Density 0.003%

    No Known Activations