© 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. 22282
    Prev
    Next
    INDEX
    Explanations

    list conjunctions and punctuation

    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
     ÑģооÑĤвеÑĤÑģÑĤвенно
    -0.06
    egner
    -0.06
     respectively
    -0.06
    åī¯æľ¬
    -0.06
    suppress
    -0.05
    onor
    -0.05
    åħīçģ¯
    -0.05
    yra
    -0.05
    ooter
    -0.05
    oubted
    -0.05
    POSITIVE LOGITS
    ear
    0.06
     Hood
    0.06
    èĮĥåĽ´
    0.05
    åĨį
    0.05
    un
    0.05
     নি
    0.05
    è°ĥ
    0.05
    ún
    0.05
    ysi
    0.05
    ood
    0.05
    Activations Density 0.043%

    No Known Activations