© 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. 10802
    Prev
    Next
    INDEX
    Explanations

    key-value assignments in code

    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
    ooks
    -0.07
    outu
    -0.06
    *R
    -0.06
    _FORE
    -0.06
    lest
    -0.06
    åĸĥ
    -0.06
    anton
    -0.06
    odem
    -0.06
    owler
    -0.06
    enius
    -0.06
    POSITIVE LOGITS
    (?:
    0.08
    交æĺĵå¸Ĥåľº
    0.07
    ertz
    0.07
    å¿«èµ°
    0.07
    iece
    0.07
    iento
    0.07
    hread
    0.07
    iesti
    0.06
    çľ¼åħī
    0.06
    bum
    0.06
    Activations Density 0.001%

    No Known Activations