© 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. 28563
    Prev
    Next
    INDEX
    Explanations

    Konva.Layer

    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
    æľĹ
    -0.06
    å½¢
    -0.06
    åıĪå¦Ĥä½ķ
    -0.06
    istic
    -0.06
    concat
    -0.06
     Federico
    -0.06
    çº
    -0.06
     concaten
    -0.06
    esh
    -0.06
    çŃĸ
    -0.06
    POSITIVE LOGITS
    orum
    0.08
    indow
    0.08
    racle
    0.08
    ána
    0.08
    æıª
    0.08
    ANH
    0.08
    assistant
    0.08
    grese
    0.08
    CharacterSet
    0.08
    anford
    0.08
    Activations Density 0.254%

    No Known Activations