© 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. 61913
    Prev
    Next
    INDEX
    Explanations

    numbers or mathematical values

    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
    éĻĦè¿ijæľī
    -0.08
    zyw
    -0.08
    åİĭåĬĽå¤§
    -0.08
    rops
    -0.08
    èĻ½æĺ¯
    -0.08
    é¦ĸåľº
    -0.08
    æ¶īåıĬ
    -0.08
    以为æĺ¯
    -0.08
    导读
    -0.08
    æĭĽ
    -0.08
    POSITIVE LOGITS
    粧
    0.07
     math
    0.06
     whatever
    0.06
    çĬ¯ç½ªåĪĨåŃIJ
    0.06
     —
    0.06
    æŁı
    0.06
    (math
    0.06
     indiv
    0.06
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    0.06
    许许å¤ļå¤ļçļĦ
    0.06
    Activations Density 0.016%

    No Known Activations