© 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. 40681
    Prev
    Next
    INDEX
    Explanations

    contractions and punctuation

    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
    -0.11
    -0.07
    eer
    -0.07
    oz
    -0.07
    Ù°
    -0.06
    erie
    -0.06
    ogr
    -0.06
    -0.06
    -ish
    -0.06
    eness
    -0.06
    POSITIVE LOGITS
    äºĭåįĬåĬŁåĢį
    0.11
    缸è¾ħ缸æĪIJ
    0.11
    身临åħ¶å¢ĥ
    0.10
    åĭĩå¾Ģ缴åīį
    0.10
    俱ä¹IJéĥ¨
    0.10
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    åĬłæĭ¿å¤§
    0.09
    ä¸įåı¯æĢĿè®®
    0.09
    è·ĥè·ĥ欲è¯ķ
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    Activations Density 0.908%

    No Known Activations