© 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. 29836
    Prev
    Next
    INDEX
    Explanations

    long, short, different, early, first

    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
    æľįåĬ¡ä¼ģä¸ļ
    -0.08
    åıĬéĻĦåĬł
    -0.08
    ftype
    -0.07
    ./(
    -0.07
    æľ¬é¢ĺåĪĨæŀIJ
    -0.07
    .$.
    -0.07
    aid
    -0.07
    ALTH
    -0.07
    æĪijçļĦæľĭåıĭ
    -0.07
    InlineData
    -0.07
    POSITIVE LOGITS
    qiq
    0.07
    niu
    0.07
    dá
    0.06
    çIJĨæīĢ
    0.06
    çĶļ
    0.06
    avent
    0.06
    åį´å¾Ī
    0.06
    天å®ĩ
    0.06
    å¹´ä¸Ń
    0.06
    yto
    0.06
    Activations Density 0.500%

    No Known Activations