© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17306
    Prev
    Next
    INDEX
    Explanations

    proper noun indicators

    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
    rief
    -0.06
    -0.06
    æĹ©æľī
    -0.06
    bie
    -0.06
    evers
    -0.06
    utie
    -0.06
     e
    -0.06
    褥
    -0.06
    æ°ĵ
    -0.06
    Own
    -0.06
    POSITIVE LOGITS
    arren
    0.08
    ijt
    0.08
    entin
    0.08
    atsu
    0.08
    olum
    0.08
    ä¼ģä¸ļçļĦåıijå±ķ
    0.08
    اÛĮØ´
    0.08
    _rng
    0.08
    çĦ¶åIJİåıĪ
    0.07
    emberg
    0.07
    Activations Density 0.008%

    No Known Activations