© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22310
    Prev
    Next
    INDEX
    Explanations

    writing instruments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èħ¾
    -0.06
    èº
    -0.05
    客
    -0.05
    ä»İä¸ļ
    -0.05
     echo
    -0.05
    Raised
    -0.05
    rep
    -0.05
    åĩºåħ¥
    -0.05
     hap
    -0.05
    Âł
    -0.04
    POSITIVE LOGITS
     pencils
    0.08
    åĬŀåħ¬å®¤éĩĮ
    0.07
    æĺ¯ä¸ĢæĶ¯
    0.07
    éĤ£èĤ¡
    0.07
    è¿ĻæĶ¯
    0.07
     pencil
    0.07
    æĸĩåħ·
    0.06
    astre
    0.06
    éĵħç¬Ķ
    0.06
    qualities
    0.06
    Activations Density 0.014%

    No Known Activations