© 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. 9241
    Prev
    Next
    INDEX
    Explanations

    solve for *d

    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
     fixe
    -0.09
    åĪ°åºŃ
    -0.08
     Poste
    -0.08
    pera
    -0.08
    _MP
    -0.08
     sema
    -0.07
    utu
    -0.07
    ä½ľèĢħæĺ¯
    -0.07
    alus
    -0.07
    _fix
    -0.07
    POSITIVE LOGITS
    oman
    0.08
    çľģçķ¥
    0.08
    à¹ģà¸Ļ
    0.07
    rys
    0.07
     omitted
    0.07
    omon
    0.07
    sport
    0.07
    aily
    0.07
    èĢĹ
    0.07
     explicit
    0.06
    Activations Density 0.195%

    No Known Activations