© 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. 18036
    Prev
    Next
    INDEX
    Explanations

    dates and try again

    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
    opak
    -0.08
    it
    -0.07
    çī¹æľĹ
    -0.06
    ìĹŃ
    -0.06
    ãy
    -0.06
     hence
    -0.06
    -0.06
    abelle
    -0.06
    orem
    -0.06
    è´¯
    -0.06
    POSITIVE LOGITS
    esso
    0.08
    elte
    0.08
    amba
    0.07
    à¹īà¸ĩ
    0.07
    ANTE
    0.07
    ivec
    0.07
    å½Į
    0.06
    ailer
    0.06
    è¿İéļ¾èĢĮä¸Ĭ
    0.06
    ponder
    0.06
    Activations Density 0.001%

    No Known Activations