© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14543
    Prev
    Next
    INDEX
    Explanations

    abroad, gradient, crossings, crit, shield

    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
    寻常
    -0.06
    æĥĬéŃĤ
    -0.06
    uf
    -0.06
     silently
    -0.06
    pta
    -0.06
     rendition
    -0.06
     Nov
    -0.06
     adaptations
    -0.05
     ÏĥÏĦά
    -0.05
    ushman
    -0.05
    POSITIVE LOGITS
    浪费äºĨ
    0.09
    å°½åı¯èĥ½
    0.09
    å°½åı¯èĥ½çļĦ
    0.09
    junk
    0.09
     вÑĭгод
    0.09
    å°½éĩıéģ¿åħį
    0.09
    å°½éĩıéĢīæĭ©
    0.09
    å°½åı¯èĥ½åľ°
    0.09
    åºĶå°½éĩı
    0.09
    å°½éĩı
    0.08
    Activations Density 0.003%

    No Known Activations