© 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. 22328
    Prev
    Next
    INDEX
    Explanations

    `end` or `post` markers

    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
    ubbo
    -0.06
    hoff
    -0.06
     repr
    -0.06
     zuletzt
    -0.05
    ******/
    -0.05
    æĢ§åĬŁèĥ½
    -0.05
    åĪĬçĻ»
    -0.05
    hots
    -0.05
    èįī
    -0.05
    zit
    -0.05
    POSITIVE LOGITS
    社ä¼ļåĮĸ
    0.06
    å®īåħ¨
    0.05
    eland
    0.05
    of
    0.05
     Of
    0.05
    ä¸ĢåľĪ
    0.05
    åŁºç¡Ģ
    0.05
    irim
    0.05
     Tim
    0.05
    第ä¸ĢæŶéĹ´
    0.05
    Activations Density 0.008%

    No Known Activations