© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46514
    Prev
    Next
    INDEX
    Explanations

    for the record

    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
    abal
    -0.08
    æĻ®éģį认为
    -0.07
    é«ĺå±±
    -0.07
    alat
    -0.07
     جÙĪ
    -0.06
    ondi
    -0.06
    æľīæķĪåľ°
    -0.06
    akat
    -0.06
    ä¸ĢæĪIJ
    -0.06
    è¦ģä¹Ī
    -0.06
    POSITIVE LOGITS
    èµ·è§ģ
    0.09
    è¿ĺåĮħæĭ¬
    0.09
    以ä¸ĭåĩłçĤ¹
    0.08
    以ä¸ĭæŃ¥éª¤
    0.07
    ä¸ĩä¸Ģ
    0.07
     includ
    0.07
    åĶłåı¨
    0.07
    ä¸Ĭè¿ĺ
    0.07
     sanity
    0.07
    ç®ķ
    0.07
    Activations Density 0.007%

    No Known Activations