© 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. 57739
    Prev
    Next
    INDEX
    Explanations

    told to + verb

    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
    angen
    -0.07
    ved
    -0.07
    cri
    -0.07
    enzi
    -0.07
    åı²æĸĻ
    -0.07
    éľĢè¦ģæıIJåīį
    -0.06
    EXTERNAL
    -0.06
    .gnu
    -0.06
     tamp
    -0.06
    illi
    -0.06
    POSITIVE LOGITS
    对æľī
    0.07
    éĩįçĤ¹ä¼ģä¸ļ
    0.07
    大æĦı
    0.06
    å°½åĬĽ
    0.06
    ippy
    0.06
    æĶ¯æµģ
    0.06
    alani
    0.06
    리ìĬ¤
    0.06
    èĬ±å¼Ģ
    0.06
    iler
    0.06
    Activations Density 0.003%

    No Known Activations