© 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. 47642
    Prev
    Next
    INDEX
    Explanations

    bibliographic entries

    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
    gur
    -0.10
    ÑĢазви
    -0.07
    ÑĤопе
    -0.07
     deteri
    -0.07
    éĤĦæĺ¯æľī
    -0.07
    istou
    -0.07
     —————————
    -0.07
    çļĦä¼ĺçĤ¹
    -0.07
    nbr
    -0.07
     ЯÑĢо
    -0.07
    POSITIVE LOGITS
    HING
    0.07
    AKER
    0.07
    åĨ³èĥľ
    0.07
    ![
    0.07
    aker
    0.07
    engel
    0.07
    ãģĹãģĭ
    0.07
    uges
    0.06
    'd
    0.06
    ãĤĤãģ®ãģ«
    0.06
    Activations Density 0.154%

    No Known Activations