© 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. 12221
    Prev
    Next
    INDEX
    Explanations

    try to imagine

    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
    oped
    -0.10
    unittest
    -0.09
    upi
    -0.09
    묻
    -0.08
    dsl
    -0.08
    äste
    -0.08
    unky
    -0.08
    nage
    -0.08
    umn
    -0.08
    rips
    -0.08
    POSITIVE LOGITS
    a
    0.07
    <
    0.07
     else
    0.07
    åħ¶ä»ĸ
    0.07
    ä¸įçĦ¶
    0.07
    A
    0.07
    '
    0.07
    æĬĢæľ¯è¿ĽæŃ¥
    0.06
    en
    0.06
    N
    0.06
    Activations Density 0.001%

    No Known Activations