© 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. 25820
    Prev
    Next
    INDEX
    Explanations

    added or extends

    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
    妥
    -0.07
    utherford
    -0.07
     Rechn
    -0.06
    稳
    -0.06
     spelling
    -0.06
     Fé
    -0.06
    西海岸
    -0.06
    MENT
    -0.06
    plor
    -0.06
    icers
    -0.06
    POSITIVE LOGITS
    æ·»åĬłåĪ°
    0.11
     added
    0.10
     Added
    0.10
    -addon
    0.10
    Added
    0.10
    added
    0.10
    æ·»
    0.10
    æ·»åĬł
    0.09
    -zero
    0.09
    Adds
    0.09
    Activations Density 0.139%

    No Known Activations