© 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. 57871
    Prev
    Next
    INDEX
    Explanations

    user, applicant, receiver, writer

    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
    porno
    -0.07
    gnore
    -0.06
    -ish
    -0.06
    sdale
    -0.06
    Ù°
    -0.06
    è¿Ļ个è¯Ŀé¢ĺ
    -0.06
    æŀľçĦ¶
    -0.06
    æī«ä¸Ģæī«
    -0.06
    /at
    -0.06
    æ¦Ĥ
    -0.06
    POSITIVE LOGITS
    ä¹ĭæīĢ
    0.09
    æīĢåľ¨åľ°åĮº
    0.08
     respective
    0.08
    èĩªå·±è¢«
    0.08
     propias
    0.08
    èĩªèº«
    0.08
    们çļĦ
    0.08
     próprias
    0.08
    's
    0.08
     respectivos
    0.08
    Activations Density 0.322%

    No Known Activations