© 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. 25331
    Prev
    Next
    INDEX
    Explanations

    probability 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
    éĩij森
    -0.08
    é«ĺéĩĩ
    -0.08
    pty
    -0.08
    macher
    -0.08
    gee
    -0.07
     phái
    -0.07
    .atan
    -0.07
    ç²Ł
    -0.07
    çĻ¾åħ¬éĩĮ
    -0.07
    eton
    -0.07
    POSITIVE LOGITS
     availability
    0.07
     available
    0.07
    æĢ»æķ°
    0.07
    åı¯ä¾Ľ
    0.07
     avail
    0.07
    availability
    0.07
    available
    0.07
     Brend
    0.07
    åı¯çĶ¨æĢ§
    0.07
    åı¯çĶ¨
    0.07
    Activations Density 0.028%

    No Known Activations