© 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. 58234
    Prev
    Next
    INDEX
    Explanations

    D&D or RPG

    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
    veen
    -0.07
    çĽijæµĭç³»ç»Ł
    -0.07
     Genome
    -0.07
    æĪĺç¥ŀ
    -0.07
     Trojan
    -0.06
    .Management
    -0.06
    éªļ
    -0.06
    å®Ŀå¡Ķ
    -0.06
    çİĭæĺŁ
    -0.06
     êµŃ민
    -0.06
    POSITIVE LOGITS
     Dungeons
    0.09
     otherwise
    0.08
     tabletop
    0.08
     wyr
    0.08
    æ´Ľå¤«
    0.07
     modifiers
    0.07
    Extras
    0.07
    chetti
    0.07
    æĸ°æµªç½ij
    0.07
    è¿Ľéĺ¶
    0.07
    Activations Density 0.319%

    No Known Activations