© 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. 37834
    Prev
    Next
    INDEX
    Explanations

    costs little, well, end, room, control, easy

    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
    ä¸įå¿ħè¦ģ
    -0.08
     unnecessary
    -0.08
    没å¿ħè¦ģ
    -0.08
    并ä¸įéľĢè¦ģ
    -0.07
    anio
    -0.07
    lega
    -0.07
    ä¸įå¿ħè¦ģçļĦ
    -0.07
    ä¹Łä¸įéľĢè¦ģ
    -0.07
    æīįèĥ½ä½¿
    -0.07
    ä¹Łä¸įå¿ħ
    -0.07
    POSITIVE LOGITS
    æ·¡
    0.08
    pret
    0.08
    å®ŀåĪĻ
    0.07
     ignoring
    0.07
     somehow
    0.07
    æ®Ĭä¸įçŁ¥
    0.07
     buc
    0.07
    enville
    0.07
    忽çķ¥
    0.07
    ès
    0.07
    Activations Density 0.143%

    No Known Activations