© 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. 38430
    Prev
    Next
    INDEX
    Explanations

    setter methods

    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
    beit
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    egger
    -0.09
    KeyId
    -0.08
    еÑĪе
    -0.08
    vre
    -0.08
    ciar
    -0.08
    Rated
    -0.08
    uvre
    -0.08
    ggi
    -0.08
    POSITIVE LOGITS
     (
    0.06
    t
    0.06
    çļĦæľĢä½³
    0.06
    ly
    0.06
     an
    0.06
     something
    0.06
    ()
    0.06
    m
    0.06
    li
    0.06
    (p
    0.06
    Activations Density 0.096%

    No Known Activations