© 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. 20900
    Prev
    Next
    INDEX
    Explanations

    magic-angle twisted, zero modes, symmetric point

    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
    elts
    -0.09
     попÑĢ
    -0.08
    ä¸įå¦Ĥ
    -0.08
    ELTS
    -0.08
    abria
    -0.08
    ÛĮÙħاÙĨ
    -0.08
    ublin
    -0.08
    ifero
    -0.08
    ëĿ½
    -0.07
    è±Ĩçĵ£è¯ĦåĪĨ
    -0.07
    POSITIVE LOGITS
    æģ°å¥½
    0.12
    æŃ£å¥½
    0.11
    å·§åIJĪ
    0.11
    åĪļ好
    0.11
    åħį
    0.10
    à¸ŀà¸Ńà¸Ķี
    0.10
    çŃīçī¹æ®Ĭ
    0.10
    åħįéĻ¤
    0.09
     coincidence
    0.09
    æģ°å·§
    0.09
    Activations Density 0.020%

    No Known Activations