© 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. 7637
    Prev
    Next
    INDEX
    Explanations

    dates, titles, authors, blessings, numbers

    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
    ölker
    -0.09
     rigged
    -0.08
    ugg
    -0.08
    次æµıè§Ī
    -0.08
    ooth
    -0.08
    BÃłi
    -0.08
    æľ¬æĢ§
    -0.08
    nö
    -0.08
    å½Ĵæł¹
    -0.08
    æľĢç»ĪåıĹçĽĬ
    -0.08
    POSITIVE LOGITS
     formatting
    0.08
    èĩªçĦ¶æ®µ
    0.07
    è§ĦèĮĥåĮĸ
    0.07
    åĨĻæ³ķ
    0.07
    æŃ£æĸĩ
    0.07
    空çĻ½
    0.07
    äºĭçĶ±
    0.07
     plain
    0.07
     format
    0.07
     formats
    0.07
    Activations Density 0.005%

    No Known Activations