© 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. 42876
    Prev
    Next
    INDEX
    Explanations

    probabilities of 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
    ernal
    -0.08
    ayos
    -0.08
    uckle
    -0.07
    ROUGH
    -0.07
    éľĢè¦ģä¸Ģ个
    -0.07
    uckles
    -0.07
    龸çİĭ
    -0.07
    criptor
    -0.07
    èĢĺ
    -0.07
    æĶĢæ¯Ķ
    -0.07
    POSITIVE LOGITS
     available
    0.11
    åı¯ä¾ĽéĢīæĭ©
    0.11
    available
    0.11
     avail
    0.10
     availability
    0.10
     disponibles
    0.10
     disponible
    0.10
     Available
    0.10
    Available
    0.09
    -available
    0.09
    Activations Density 0.050%

    No Known Activations