© 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. 18906
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words like 'per' or 'from'

    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
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    åı£åŃIJ
    -0.06
    coli
    -0.06
    igan
    -0.06
     ARGS
    -0.06
    ldb
    -0.06
    åħ³å¿ĥçļĦ
    -0.06
    è¡¥
    -0.06
    å°Ķ夫
    -0.06
    顾åIJįæĢĿ
    -0.06
    POSITIVE LOGITS
    åĪļ好
    0.11
    æŃ£å¥½
    0.10
     coinc
    0.10
    åīĽå¥½
    0.09
    çĨŁæĤī
    0.09
    ãģ¡ãĤĩãģĨãģ©
    0.09
     coincid
    0.09
    çĨŁæĤīçļĦ
    0.09
    æģ°å¥½
    0.08
    æģ°å·§
    0.08
    Activations Density 0.120%

    No Known Activations