© 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. 3734
    Prev
    Next
    INDEX
    Explanations

    place where

    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
    isinde
    -0.07
    æľĪä¸Ĭ
    -0.07
    çĴŁ
    -0.07
    úc
    -0.07
    ä¼ģä¸ļåıĬ
    -0.07
     therein
    -0.07
    _FUN
    -0.07
    å¹´å§ĭ
    -0.07
    ports
    -0.06
    Ñģал
    -0.06
    POSITIVE LOGITS
     hopefully
    0.09
     processed
    0.08
     valid
    0.07
     <=
    0.07
    å½ĵåīį
    0.07
    éĩįéĩij
    0.07
     vur
    0.07
    ä¹İ
    0.07
     prov
    0.07
    elsen
    0.07
    Activations Density 0.010%

    No Known Activations