© 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. 12432
    Prev
    Next
    INDEX
    Explanations

    eternal life, regeneration, first day, shared libraries

    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
    коÑģ
    -0.08
    azy
    -0.08
    ystone
    -0.08
    eya
    -0.08
    ány
    -0.08
    åİ»çİ©
    -0.08
    getExtension
    -0.07
    ÑĢк
    -0.07
    comed
    -0.07
    ãĥĥãĤµ
    -0.07
    POSITIVE LOGITS
     âĢ¦
    0.09
    âĢ¦âĢ¦
    0.09
     [
    0.09
     .
    0.07
    è´ŀ
    0.06
     [âĢ¦]
    0.06
    ä¹ĭæīĢ
    0.06
    �
    0.06
    åīį款
    0.06
    [
    0.06
    Activations Density 0.025%

    No Known Activations