© 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. 50576
    Prev
    Next
    INDEX
    Explanations

    male or female descriptors

    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
    Ø©
    -0.10
    ively
    -0.08
    çļĦ人è¿ĺ
    -0.08
    ation
    -0.07
    ahuan
    -0.07
    iems
    -0.07
    orative
    -0.07
    ¡
    -0.07
    好èĩªå·±çļĦ
    -0.07
    ümer
    -0.07
    POSITIVE LOGITS
    volent
    0.13
    ities
    0.10
    itarian
    0.10
    cule
    0.10
    hood
    0.09
    -authored
    0.09
    idades
    0.09
    -headed
    0.09
    ½
    0.09
    itÃł
    0.08
    Activations Density 0.033%

    No Known Activations