© 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. 19950
    Prev
    Next
    INDEX
    Explanations

    forum posts and comments

    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
     Lorem
    -0.08
    çĿĢåij¢
    -0.08
    bcc
    -0.07
    \xd
    -0.07
    æ·±åıĹ广大
    -0.07
    agak
    -0.07
    ãģŀ
    -0.07
    å±ħæ°ij身份è¯ģ
    -0.07
    agine
    -0.07
    ¬ģ
    -0.07
    POSITIVE LOGITS
    kat
    0.08
    uga
    0.06
    _secret
    0.06
    achat
    0.06
     secret
    0.06
    SourceType
    0.06
    çĥŃéŨæIJľç´¢
    0.06
    å¯¹æľ¬æ¬¡
    0.06
    æĸ¹æ³ķåıĬ
    0.06
     fer
    0.06
    Activations Density 0.001%

    No Known Activations