© 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. 47154
    Prev
    Next
    INDEX
    Explanations

    method and

    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
    [dir
    -0.08
    çĿ¹
    -0.08
    echos
    -0.08
    awang
    -0.07
    Locator
    -0.07
    verty
    -0.07
    ازÛĮ
    -0.07
     articul
    -0.07
    diri
    -0.07
    çĻ½éľ²
    -0.07
    POSITIVE LOGITS
     process
    0.09
    è¿ĩç¨ĭ
    0.08
     пÑĢоÑĨеÑģÑģ
    0.08
    process
    0.07
    æŃ¥éª¤
    0.07
    æµģç¨ĭ
    0.07
    åĬ¨ä½ľ
    0.07
    çļĦåħ¨è¿ĩç¨ĭ
    0.07
     actions
    0.07
     performed
    0.07
    Activations Density 0.110%

    No Known Activations