© 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. 3872
    Prev
    Next
    INDEX
    Explanations

    requests for help

    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
    ings
    -0.09
    ifax
    -0.09
    oux
    -0.08
    åħ®
    -0.08
    TRS
    -0.08
    AXB
    -0.08
    øk
    -0.08
    iven
    -0.08
    <|box_end|>
    -0.08
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.07
    为æѤ
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    hte
    0.07
    å®ĥä¸İ
    0.07
    eight
    0.07
    :
    0.07
    s
    0.07
    ellen
    0.07
    spiel
    0.07
    Activations Density 0.002%

    No Known Activations