© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34915
    Prev
    Next
    INDEX
    Explanations

    special characters or "through" or "by"

    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
    Negative Logits
    enticate
    -0.10
    IgnoreCase
    -0.08
    оваÑĤÑĮ
    -0.07
    ening
    -0.07
    -dismiss
    -0.07
    Ñĥне
    -0.07
    ensed
    -0.07
    Ùħاش
    -0.07
    вид
    -0.07
    éľīç´ł
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæĸ¹å¼ı
    0.16
    è¿Ļç§įæĸ¹å¼ı
    0.11
    åħ¶ä»ĸæĸ¹å¼ı
    0.11
    å¤ļç§įæĸ¹å¼ı
    0.10
    çİĩé«ĺ
    0.10
    ़
    0.10
    以ä¸ĭæŃ¥éª¤
    0.10
    oj
    0.09
    ä»ĸæĿ¥
    0.09
    æŁIJç§į
    0.09
    Activations Density 0.001%

    No Known Activations