© 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. 22411
    Prev
    Next
    INDEX
    Explanations

    creating or defining actions

    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
    Negative Logits
    å¦Ĥæŀľèĥ½å¤Ł
    -0.06
    æľĿçĿĢ
    -0.06
    åı¯æݧ
    -0.06
    ç¿»
    -0.06
    kÅĤad
    -0.05
    åIJijåĸĦ
    -0.05
    åĪ®
    -0.05
    梢
    -0.05
    ÏĦοÏĢοι
    -0.05
    大åIJĮ
    -0.05
    POSITIVE LOGITS
    punt
    0.06
    以åıĬ对
    0.05
    idi
    0.05
    rance
    0.05
     importance
    0.05
    æĥħç»ĵ
    0.05
     punt
    0.05
    гÑĢаÑĦи
    0.05
    omit
    0.05
    lest
    0.05
    Activations Density 0.043%

    No Known Activations