© 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. 41026
    Prev
    Next
    INDEX
    Explanations

    e.g.,

    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
    anut
    -0.07
     presumably
    -0.07
    isky
    -0.07
    çĤ¹æѤ
    -0.07
    anam
    -0.07
     kinky
    -0.07
    dera
    -0.07
    unden
    -0.06
    _ASSUME
    -0.06
    åħ¶
    -0.06
    POSITIVE LOGITS
     halnya
    0.11
    ä¸įéĻIJäºİ
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.08
     celles
    0.08
    jenigen
    0.08
    ()",
    0.08
     ones
    0.07
     those
    0.07
     quelli
    0.07
     próprio
    0.07
    Activations Density 0.113%

    No Known Activations