© 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. 31242
    Prev
    Next
    INDEX
    Explanations

    parse, creates, is

    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
     relevante
    -0.08
    леб
    -0.08
    ·
    -0.07
    andong
    -0.07
    anski
    -0.07
    åĪĨæŀIJåıĬ
    -0.07
    iban
    -0.07
    ÐĽÐŀÐĴ
    -0.07
    山人
    -0.07
    _contains
    -0.07
    POSITIVE LOGITS
    :param
    0.08
     {@
    0.07
    æħ·
    0.07
     Tender
    0.07
    ë¡Ģ
    0.06
     helper
    0.06
    ezd
    0.06
    ldr
    0.06
    \param
    0.06
    åİ¿æķĻèĤ²å±Ģ
    0.06
    Activations Density 0.019%

    No Known Activations