© 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. 27458
    Prev
    Next
    INDEX
    Explanations

    please followed by an action

    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
    iet
    -0.08
    scan
    -0.07
    ans
    -0.07
    sw
    -0.07
    yssey
    -0.07
    illac
    -0.07
    ients
    -0.07
    ÑģÑĤно
    -0.07
    ysz
    -0.06
    нÑĥÑģ
    -0.06
    POSITIVE LOGITS
    ftware
    0.07
    à¥Ģल
    0.07
    çļĭ
    0.07
    æĺ¯åĽ½åĨħ
    0.07
    onato
    0.06
    geld
    0.06
    ledes
    0.06
    OPTION
    0.06
    anja
    0.06
    bbe
    0.06
    Activations Density 0.022%

    No Known Activations