© 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. 47102
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation

    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
    dn
    -0.07
    ÙĪÙĦÙĬÙĨ
    -0.07
    új
    -0.07
    çIJĨæīĢ
    -0.07
    ierge
    -0.06
    åij½
    -0.06
    rech
    -0.06
    SAT
    -0.06
    åŀ«
    -0.06
    صب
    -0.06
    POSITIVE LOGITS
    ower
    0.07
    laud
    0.07
    OWER
    0.07
    cxx
    0.07
    emani
    0.07
    åħħåĪĨè°ĥåĬ¨
    0.07
    ohon
    0.07
    riad
    0.06
     (*
    0.06
    æĬ½è°ĥ
    0.06
    Activations Density 0.007%

    No Known Activations