© 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. 33371
    Prev
    Next
    INDEX
    Explanations

    downloading files or URLs

    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
    eenth
    -0.12
     Hinblick
    -0.10
    à¯įà®Ł
    -0.10
    deaux
    -0.10
    ÙĤاÙħØ©
    -0.09
    rades
    -0.09
    enner
    -0.09
    ucho
    -0.09
    Cola
    -0.09
    ober
    -0.09
    POSITIVE LOGITS
    most
    0.10
    elling
    0.09
    /up
    0.08
    /out
    0.07
    ¼
    0.07
    /down
    0.07
    à¹Ģรืà¹Īà¸Ńยà¹Ĩ
    0.07
    ings
    0.07
    stry
    0.07
    stract
    0.07
    Activations Density 0.081%

    No Known Activations