© 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. 23349
    Prev
    Next
    INDEX
    Explanations

    z expression suffix

    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
    ly
    -0.08
    al
    -0.07
    iefer
    -0.07
    份
    -0.06
    en
    -0.06
    stead
    -0.06
    o
    -0.06
    ra
    -0.06
    ing
    -0.06
    rada
    -0.06
    POSITIVE LOGITS
    æł¼å¼ıçļĦ
    0.09
    @(
    0.08
    jets
    0.08
    æĹłå¤Ħ
    0.08
    ipa
    0.08
    keh
    0.08
    èĩªè¨Ģèĩªè¯Ń
    0.08
    ezu
    0.08
    enate
    0.08
     overd
    0.08
    Activations Density 0.003%

    No Known Activations