© 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. 32844
    Prev
    Next
    INDEX
    Explanations

    first positions or beginnings

    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
     trì
    -0.07
    essenger
    -0.07
    rer
    -0.07
    ê³±
    -0.07
    .retry
    -0.06
    .instrument
    -0.06
    åĪĨæķ°
    -0.06
     hél
    -0.06
    交æµģä¸İåIJĪä½ľ
    -0.06
    aringan
    -0.06
    POSITIVE LOGITS
    æĹłåīį
    0.10
    å§ĭ
    0.08
     special
    0.08
    å¤ĸéĥ¨
    0.07
    åĪĿ
    0.07
     maiden
    0.07
    çī¹æ®ĬçļĦ
    0.07
     Initial
    0.07
    loss
    0.07
    ä»ħæľīçļĦ
    0.07
    Activations Density 0.024%

    No Known Activations