© 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. 31059
    Prev
    Next
    INDEX
    Explanations

    Porn online

    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
    èĩªå·±
    -0.07
    èĩªå·±è¢«
    -0.06
    åij¨ä¸Ģèĩ³
    -0.06
    ï¼ĮãĢĬ
    -0.06
    Ñĥл
    -0.06
     underlying
    -0.06
    “
    -0.06
    inema
    -0.06
    ,
    -0.06
    ultip
    -0.06
    POSITIVE LOGITS
    äºĭåįĬåĬŁåĢį
    0.12
    身临åħ¶å¢ĥ
    0.10
    ä¸įåı¯æĢĿè®®
    0.10
    èĢ³çĨŁèĥ½è¯¦
    0.10
    åĭĩå¾Ģ缴åīį
    0.10
    åħ¨å¿ĥåħ¨æĦı
    0.09
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.09
    两åѦä¸Ģåģļ
    0.09
    çĦ¶æĺ¯
    0.09
    efined
    0.08
    Activations Density 0.002%

    No Known Activations