© 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. 2094
    Prev
    Next
    INDEX
    Explanations

    plug in, maid, heater in

    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
    getc
    -0.08
    åݻ认è¯ģ
    -0.07
    åģļ强
    -0.07
    дав
    -0.07
    ê³µì§Ģ
    -0.07
    usern
    -0.07
    _READONLY
    -0.07
    pgsql
    -0.07
    æĪijè¦ģæĬķè¯ī
    -0.07
    credential
    -0.07
    POSITIVE LOGITS
    _cmds
    0.08
     ...
    0.08
    åĤ¢
    0.07
     abstract
    0.06
     additionally
    0.05
    à¸ĩ
    0.05
    acking
    0.05
    orida
    0.05
    æıIJ
    0.05
    ...
    0.05
    Activations Density 0.067%

    No Known Activations