© 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. 20714
    Prev
    Next
    INDEX
    Explanations

    Heisenberg, Ising, IBM

    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
    sert
    -0.09
    ivate
    -0.09
    enef
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    hin
    -0.08
    ients
    -0.08
    isseur
    -0.08
    Å¡in
    -0.08
    两åѦä¸Ģåģļ
    -0.08
    irse
    -0.08
    POSITIVE LOGITS
    operators
    0.07
    hower
    0.07
    (encoding
    0.07
    ÙĥÙĬØ©
    0.07
    ernen
    0.07
    ¶
    0.07
    breaking
    0.06
    ×ķש
    0.06
    ä¸ĩå²ģ
    0.06
    çīĪ
    0.06
    Activations Density 0.001%

    No Known Activations