© 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. 43331
    Prev
    Next
    INDEX
    Explanations

    define structures or rules

    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
    ../../../
    -0.09
    anser
    -0.09
    smith
    -0.08
    ten
    -0.08
    ../../
    -0.08
    нÑĸм
    -0.08
    teni
    -0.08
    aventure
    -0.08
    ouse
    -0.07
    Äģk
    -0.07
    POSITIVE LOGITS
    veloper
    0.11
    inition
    0.10
    isikan
    0.09
     ulang
    0.09
    jenigen
    0.08
    ä¸įæ¸ħ
    0.08
    tte
    0.08
    eer
    0.08
    velopment
    0.08
    ydd
    0.08
    Activations Density 0.081%

    No Known Activations