© 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. 16758
    Prev
    Next
    INDEX
    Explanations

    unit/time specifications

    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
    çĪµå£«
    -0.08
     Barg
    -0.08
    yton
    -0.07
    åº
    -0.07
    夫åIJĽ
    -0.07
    osz
    -0.07
    upaya
    -0.07
    _SIM
    -0.07
    ì§
    -0.07
    Aliases
    -0.07
    POSITIVE LOGITS
    并ä¸į容æĺĵ
    0.07
    htt
    0.07
    ä¸į好
    0.06
    伦
    0.06
    ayer
    0.06
    uta
    0.06
     Griffith
    0.06
    忽çĦ¶
    0.06
    orph
    0.06
    Ñħан
    0.06
    Activations Density 0.017%

    No Known Activations