© 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. 23296
    Prev
    Next
    INDEX
    Explanations

    list partitioning or number sequences

    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
    Ñģел
    -0.07
    éľĢè¦ģæıIJåīį
    -0.07
    åįł
    -0.06
    ä¸Ģ大
    -0.06
    åİŁåĪĻä¸Ĭ
    -0.06
     wig
    -0.06
    uko
    -0.06
    åıªè¦ģä½ł
    -0.06
    asih
    -0.06
     ith
    -0.06
    POSITIVE LOGITS
    æī¾åĩº
    0.09
    è¯ĨåĪ«
    0.09
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.08
    è¾¾æĭī
    0.08
    éĢIJ个
    0.08
    adoo
    0.07
    认å®ļçļĦ
    0.07
    æĺİæĺ¾çļĦ
    0.07
    Interop
    0.07
     manually
    0.07
    Activations Density 0.007%

    No Known Activations