© 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. 26349
    Prev
    Next
    INDEX
    Explanations

    .com addresses

    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
    èªł
    -0.08
    enna
    -0.08
    alc
    -0.07
    /dc
    -0.07
    æľĪçĶŁ
    -0.07
    çī©ç¾İ
    -0.07
    Ç
    -0.07
    è¯ļ
    -0.07
    _txn
    -0.07
    ioc
    -0.07
    POSITIVE LOGITS
    大åıij
    0.08
    бин
    0.08
    wali
    0.07
    osit
    0.07
    ANGAN
    0.07
    _BU
    0.07
    âķĹ
    0.06
    aderno
    0.06
    utori
    0.06
    ickl
    0.06
    Activations Density 0.226%

    No Known Activations