© 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. 32678
    Prev
    Next
    INDEX
    Explanations

    founder or earliest entity

    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
    åİĨå¹´
    -0.08
    è¿ijåĩłå¹´
    -0.08
    æľĢè¿ijåĩłå¹´
    -0.08
     currently
    -0.07
    éļ¾åħį
    -0.07
     presently
    -0.07
     evolve
    -0.07
    -io
    -0.07
    è¿ijåĩłå¹´æĿ¥
    -0.06
     occasionally
    -0.06
    POSITIVE LOGITS
    以éĻį
    0.10
    åīįæīĢæľªæľīçļĦ
    0.09
    æŀģå¤§åľ°
    0.09
     onward
    0.09
     famously
    0.09
    天æīį
    0.08
    å¥ł
    0.08
     onwards
    0.08
    å¼ķåħ¥äºĨ
    0.08
    -era
    0.08
    Activations Density 0.060%

    No Known Activations