© 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. 34172
    Prev
    Next
    INDEX
    Explanations

    specific names and individuals

    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
    igna
    -0.09
     à¸ķà¸²à¸¡à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    -0.08
     Sole
    -0.07
    воен
    -0.07
    å¿ĥçĶĺ
    -0.07
    çĪ±å²Ĺ
    -0.07
    usser
    -0.07
    brem
    -0.07
    çļĦ缸åħ³è§Ħå®ļ
    -0.07
    dad
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵçļĦ
    0.13
    åħ·ä½ĵ
    0.11
    çļĦåħ·ä½ĵ
    0.11
    åħ·é«Ķ
    0.11
    åħ·ä½ĵéĹ®é¢ĺ
    0.10
     конкÑĢеÑĤнÑĭÑħ
    0.10
    åħ·ä½ĵçļĦãģª
    0.10
     конкÑĢеÑĤ
    0.09
     konkrét
    0.09
     specific
    0.09
    Activations Density 0.009%

    No Known Activations