© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15028
    Prev
    Next
    INDEX
    Explanations

    love, enjoy, celebrate

    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
    acket
    -0.08
    Ñijн
    -0.07
    ousel
    -0.07
    ebt
    -0.07
    ROTO
    -0.07
    umbed
    -0.07
    æıIJä¾ĽåıĤèĢĥ
    -0.07
    reich
    -0.07
    écr
    -0.07
    stående
    -0.07
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.07
    isme
    0.06
     pula
    0.06
    颱
    0.06
    ÑıÑĢ
    0.06
    Âł
    0.06
    nga
    0.06
    Ľ
    0.06
    KU
    0.06
    åħħæĸ¥
    0.06
    Activations Density 0.471%

    No Known Activations