© 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. 22312
    Prev
    Next
    INDEX
    Explanations

    goalkeeper or goalie

    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
    amba
    -0.06
    amble
    -0.06
    ikasi
    -0.06
    å°ıç»Ħ
    -0.05
    ulos
    -0.05
    omm
    -0.05
    aldi
    -0.05
    éĢŁåº¦ä¸İ
    -0.05
    ultur
    -0.05
    ä¹ł
    -0.05
    POSITIVE LOGITS
    åĢ¼çıŃ
    0.06
     reca
    0.06
    è¢Ĵ
    0.06
    ural
    0.06
    един
    0.06
    士æŀĹ
    0.06
    æ¢Ĩ
    0.05
    wayne
    0.05
    arium
    0.05
    é»ijè¡£
    0.05
    Activations Density 0.019%

    No Known Activations