© 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. 45383
    Prev
    Next
    INDEX
    Explanations

    research papers and citations

    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
    aksin
    -0.09
    chini
    -0.09
    ukul
    -0.09
    Pieces
    -0.09
    ajak
    -0.08
    !!:
    -0.08
     arras
    -0.08
     famously
    -0.08
    人家
    -0.08
    andal
    -0.08
    POSITIVE LOGITS
    次æµıè§Ī
    0.06
    ent
    0.06
     âĢ
    0.06
    æļĤæĹł
    0.06
     âĸ
    0.06
    ´
    0.06
     ranging
    0.06
    áĪĪ
    0.06
    bh
    0.06
     Alter
    0.06
    Activations Density 0.003%

    No Known Activations