© 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. 40100
    Prev
    Next
    INDEX
    Explanations

    result / yielding

    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
    ile
    -0.08
    agination
    -0.07
    å¨ĥ
    -0.07
     Gall
    -0.07
    éĹ
    -0.07
     Freak
    -0.07
    anka
    -0.07
    ÑĢÑĥбе
    -0.07
    顧
    -0.06
    à§įর
    -0.06
    POSITIVE LOGITS
    ç»ĵæŀľä¸º
    0.10
    ç»ĵæŀľæĺ¯
    0.09
     ergibt
    0.09
     resulting
    0.08
     yielding
    0.08
    è¿Ļä¸įä»ħ
    0.07
    elj
    0.07
    ixo
    0.07
    kla
    0.07
    ç»ĵæŀľ
    0.07
    Activations Density 0.022%

    No Known Activations