© 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. 15227
    Prev
    Next
    INDEX
    Explanations

    human sexuality

    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
    essel
    -0.08
    icale
    -0.07
    orraine
    -0.07
    orr
    -0.07
    é£İ声
    -0.07
    okuva
    -0.06
    TITLE
    -0.06
    orate
    -0.06
     Seas
    -0.06
    aison
    -0.06
    POSITIVE LOGITS
    èĢħä¼ĺåħĪ
    0.09
    insk
    0.08
    erb
    0.07
    çħ§çĽ¸
    0.07
     Went
    0.07
    awi
    0.07
    å¼Ģ好
    0.07
    ikas
    0.07
    åįģåĽĽäºĶ
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    Activations Density 0.033%

    No Known Activations