© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23445
    Prev
    Next
    INDEX
    Explanations

    evidence-based

    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
    ients
    -0.10
    IMUM
    -0.10
    adies
    -0.08
    raries
    -0.07
    ish
    -0.07
     ìĿ¸íķ´
    -0.07
    er
    -0.07
    ackle
    -0.07
    izations
    -0.07
    gether
    -0.07
    POSITIVE LOGITS
    haft
    0.10
    itious
    0.08
    lessly
    0.08
    ação
    0.07
    ä¹ĭä¸Ģæĺ¯
    0.07
    IVEN
    0.07
    iveness
    0.07
    ноÑģÑĤ
    0.07
    abox
    0.07
    iglio
    0.07
    Activations Density 0.025%

    No Known Activations