© 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. 8291
    Prev
    Next
    INDEX
    Explanations

    starts scrolling

    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
    adelph
    -0.07
    æ·¡éĽħ
    -0.07
    æ·ij
    -0.07
    åıĪåĪ°
    -0.07
    ç¥ŀæĢ¡
    -0.07
    缸å¾ĹçĽĬå½°
    -0.07
    prites
    -0.07
    åī¯ç§ĺ书éķ¿
    -0.07
    gent
    -0.06
    fahr
    -0.06
    POSITIVE LOGITS
    è¿ĻæŶçļĦ
    0.13
    æѤæŶçļĦ
    0.11
    ä¸įåĨįæĺ¯
    0.11
    è¿ĻæŶ
    0.11
    ä¸įèĥ½åĨį
    0.10
    å·²ç»ıä¸įæĺ¯
    0.10
    æѤæŶ
    0.10
    ä¸įåĨįæľī
    0.10
    ä¸įåĨį
    0.09
     ÏĢλÎŃον
    0.09
    Activations Density 0.014%

    No Known Activations