© 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. 22281
    Prev
    Next
    INDEX
    Explanations

    lists, facts, tips

    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
     ÑĢазбоÑĢ
    -0.06
    rück
    -0.06
    ridge
    -0.06
    elli
    -0.06
    omon
    -0.06
    eries
    -0.05
     giác
    -0.05
     gầm
    -0.05
     sämt
    -0.05
    èĩªèįIJ
    -0.05
    POSITIVE LOGITS
    )':
    0.06
    )):
    0.06
     ter
    0.06
    éĿ¶
    0.05
    }):
    0.05
    åĮĹç«Ļ
    0.05
    bill
    0.05
     ma
    0.05
     envol
    0.05
     vac
    0.05
    Activations Density 0.012%

    No Known Activations