© 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. 63532
    Prev
    Next
    INDEX
    Explanations

    .Forms, INC, Caps, -format

    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
    igni
    -0.08
     ','.
    -0.07
    ither
    -0.07
     //-
    -0.07
    acor
    -0.07
     {}",
    -0.07
    ثة
    -0.07
    رة
    -0.07
    åķĨæľº
    -0.07
    orc
    -0.07
    POSITIVE LOGITS
    çĿ¦
    0.07
     inh
    0.07
     being
    0.07
     étant
    0.07
    å·±
    0.06
    æĥ®
    0.06
    天主
    0.06
     Parkway
    0.06
    arme
    0.06
    å½Ĵ
    0.06
    Activations Density 0.171%

    No Known Activations