© 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. 8630
    Prev
    Next
    INDEX
    Explanations

    original / originally

    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
    eps
    -0.07
    æ±IJ
    -0.07
    αÏģα
    -0.07
    clud
    -0.07
    å®¹é¢ľ
    -0.06
    aliste
    -0.06
     arity
    -0.06
    ispo
    -0.06
     Armed
    -0.06
    ologe
    -0.06
    POSITIVE LOGITS
    åİŁå§ĭçļĦ
    0.12
    æľĢåĪĿçļĦ
    0.11
     Original
    0.10
     иÑģÑħод
    0.10
    åİŁå§ĭ
    0.10
    original
    0.10
    Original
    0.09
    /original
    0.09
    åİŁæľīçļĦ
    0.09
     originally
    0.09
    Activations Density 0.691%

    No Known Activations