© 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. 3236
    Prev
    Next
    INDEX
    Explanations

    update after add or part

    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
    eba
    -0.07
    ellent
    -0.07
    loy
    -0.06
    awe
    -0.06
    .Global
    -0.06
    master
    -0.06
    els
    -0.06
     Arena
    -0.06
    ìħĢ
    -0.06
     Listing
    -0.06
    POSITIVE LOGITS
    补足
    0.08
    å°Ķåħĭ
    0.07
    borgen
    0.07
    reon
    0.07
     alone
    0.07
    åįķçĭ¬
    0.07
    alone
    0.07
     supplementary
    0.06
    è¡¥
    0.06
    åĬłåĪĨ
    0.06
    Activations Density 0.001%

    No Known Activations