© 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. 60199
    Prev
    Next
    INDEX
    Explanations

    ONE, ZERO, TWO, FEW, MANY, OTHER

    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
    cept
    -0.07
    itten
    -0.07
    ukka
    -0.06
     عÙĦ
    -0.06
    ancier
    -0.06
    ÙĤ
    -0.06
    engel
    -0.06
    usia
    -0.06
     Ãļlt
    -0.06
    ött
    -0.06
    POSITIVE LOGITS
    <|fim_suffix|>
    0.08
     Ejem
    0.08
    ouro
    0.08
     mantu
    0.08
    åİĭåĢĴ
    0.07
     Leban
    0.07
     diserta
    0.07
    \Id
    0.07
    æĮĸæİĺåħ¬åı¸
    0.07
    wany
    0.07
    Activations Density 0.126%

    No Known Activations