© 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. 32847
    Prev
    Next
    INDEX
    Explanations

    respectively

    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
    æ¯Ķå¦Ĥ说
    -0.09
    èѬå¦Ĥ
    -0.09
    æ¯Ķå¦Ĥ
    -0.08
    ãģŁãģ¨ãģĪãģ°
    -0.08
    æį¢åı¥è¯Ŀ说
    -0.08
    åį³çĶ¨
    -0.08
    åį³åľ¨
    -0.08
    åį³ä»¥
    -0.08
    åį³åĪ°
    -0.08
     (âĢŀ
    -0.08
    POSITIVE LOGITS
    è¿Ļåľ¨
    0.08
    uter
    0.08
     which
    0.08
    .which
    0.06
    .between
    0.06
    uters
    0.06
    ador
    0.06
    è¿Ļåı¯èĥ½æĺ¯
    0.06
     disb
    0.06
    è¿Ļä¹Łæĺ¯
    0.06
    Activations Density 0.175%

    No Known Activations