© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22847
    Prev
    Next
    INDEX
    Explanations

    connection and parallel vector

    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
    ipher
    -0.09
    åİħéķ¿
    -0.08
    ÃĩO
    -0.08
    ossal
    -0.08
    åī¯çľģéķ¿
    -0.08
    è¿Ļ个æķ°åŃĹ
    -0.07
    çľģéķ¿
    -0.07
     contest
    -0.07
    åĩīæ°´
    -0.07
    ÑĢаÑĨиÑı
    -0.07
    POSITIVE LOGITS
    enstein
    0.08
    ffi
    0.07
    ahir
    0.07
     gratuit
    0.07
     tensors
    0.07
     Einstein
    0.07
     tensor
    0.06
    æĿ¾
    0.06
    åħīæ»ij
    0.06
    被èªī为
    0.06
    Activations Density 0.008%

    No Known Activations