© 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. 7931
    Prev
    Next
    INDEX
    Explanations

    story collection

    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
    èIJ½æĪIJ
    -0.07
    oule
    -0.07
    çķħéĢļ
    -0.07
    asn
    -0.07
    æ²ŁéĢļåįıè°ĥ
    -0.07
    é»Ļ
    -0.07
    oly
    -0.07
    çģ
    -0.06
     Pes
    -0.06
    Pes
    -0.06
    POSITIVE LOGITS
     questionable
    0.08
    æ··æIJŃ
    0.07
    /prom
    0.07
    inken
    0.07
    ÅĽÄĩ
    0.07
    æĺ¯åIJ¦æŃ£ç¡®
    0.07
    iete
    0.07
    chaft
    0.06
    ether
    0.06
     correctly
    0.06
    Activations Density 0.001%

    No Known Activations