© 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. 44057
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
     Svens
    -0.07
    ulut
    -0.07
    entos
    -0.07
    ارا
    -0.06
    arb
    -0.06
    Calls
    -0.06
    oke
    -0.06
    quit
    -0.06
    itera
    -0.06
    วà¸ģ
    -0.06
    POSITIVE LOGITS
    PropTypes
    0.07
    è¡¡
    0.07
    åĪ·
    0.07
    æĪijéĤ£
    0.07
    æį®è¯´
    0.07
    æ¯į
    0.06
    ioni
    0.06
    导
    0.06
    ç»İ
    0.06
    ác
    0.06
    Activations Density 0.022%

    No Known Activations