© 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. 64856
    Prev
    Next
    INDEX
    Explanations

    aligned sequences

    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
    jure
    -0.08
    rong
    -0.08
    unar
    -0.08
    yek
    -0.08
    áĢº
    -0.08
    incr
    -0.07
    пина
    -0.07
    appers
    -0.07
    onas
    -0.07
     promen
    -0.07
    POSITIVE LOGITS
    åİŁæľī
    0.12
     existing
    0.12
     Existing
    0.11
    Existing
    0.11
    existing
    0.10
    çİ°æľī
    0.10
    (existing
    0.10
    åİŁæľīçļĦ
    0.09
    å·²æľīçļĦ
    0.09
    çİ°æľīçļĦ
    0.09
    Activations Density 0.112%

    No Known Activations