© 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. 2960
    Prev
    Next
    INDEX
    Explanations

    adjectives and word endings

    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
    身ä¸Ĭä¸ĭ
    -0.08
    ;**
    -0.08
    ä¹İåħ¶
    -0.08
    jenigen
    -0.07
    òng
    -0.07
    aisser
    -0.07
    æĺ¯ä¸Ģ大
    -0.07
    acca
    -0.07
    ['__
    -0.07
    antly
    -0.07
    POSITIVE LOGITS
    ...
    0.07
    ?:
    0.07
    åįĥä¸ĩ
    0.06
    ..."
    0.06
    çļĦäºĭåĦ¿
    0.06
    åħ´åįİ
    0.06
     ...
    0.06
    åı¬
    0.06
    jum
    0.06
     vs
    0.06
    Activations Density 1.084%

    No Known Activations