© 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. 63323
    Prev
    Next
    INDEX
    Explanations

    particular thing or case

    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
    à¹īà¸ĩ
    -0.10
    cape
    -0.09
    ðŁĺĢ
    -0.09
    egal
    -0.09
    uropa
    -0.08
    viles
    -0.08
    à¸ģารà¸ķลาà¸Ķ
    -0.08
    pected
    -0.08
    elij
    -0.08
    urator
    -0.08
    POSITIVE LOGITS
    ities
    0.16
    ity
    0.09
    ized
    0.09
    ately
    0.08
    istic
    0.08
     halnya
    0.08
    ization
    0.08
    ÃŃsimo
    0.08
    ièrement
    0.08
    à¹Ģà¸Īาะ
    0.08
    Activations Density 0.065%

    No Known Activations