© 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. 28385
    Prev
    Next
    INDEX
    Explanations

    food products and technology

    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
    á»ķ
    -0.07
    oise
    -0.07
    ezer
    -0.07
    Ļ
    -0.07
    éĢģä¸Ģ
    -0.06
    åļı
    -0.06
    çĴŀ
    -0.06
    ç¾Ĭæ¯Ľ
    -0.06
     headaches
    -0.06
    ìĤ¬íķŃ
    -0.06
    POSITIVE LOGITS
    borne
    0.10
    enius
    0.09
    æ®ĭ渣
    0.09
    fulness
    0.09
    (food
    0.09
    ç¾İåij³
    0.08
    ä¸Ģé¡¿
    0.08
    ä½³èĤ´
    0.08
    -food
    0.08
    liness
    0.08
    Activations Density 0.116%

    No Known Activations