© 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. 29327
    Prev
    Next
    INDEX
    Explanations

    relative directory paths

    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
    raction
    -0.07
    举èĩ³
    -0.07
    楼ä¸Ĭ
    -0.07
    计ç®Ĺæľºè½¯ç¡¬ä»¶
    -0.07
    inh
    -0.07
    è®¤çľŁåģļ好
    -0.07
    ãĥ«ãĥ¼ãĥł
    -0.07
    活泼
    -0.07
    olate
    -0.06
    çģ«çĥ§
    -0.06
    POSITIVE LOGITS
    صÙĦ
    0.08
    aries
    0.07
    ãģµ
    0.07
    æĶ¿æ²»
    0.07
    lobs
    0.07
    ertz
    0.06
    falls
    0.06
    客
    0.06
     ÙĪبÙĬÙĨ
    0.06
     osnov
    0.06
    Activations Density 0.125%

    No Known Activations