© 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. 22289
    Prev
    Next
    INDEX
    Explanations

    legal citations and parties

    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
     doss
    -0.06
    èĢĥçļĦ
    -0.06
     dø
    -0.06
     revers
    -0.06
    olec
    -0.06
    вно
    -0.05
    reens
    -0.05
    ä¸ĵåįĸ
    -0.05
    .trade
    -0.05
    ÃģC
    -0.05
    POSITIVE LOGITS
    endi
    0.06
    hausen
    0.06
    æ¶Ĥ
    0.05
    åħ«
    0.05
    ighet
    0.05
    inger
    0.05
    uto
    0.05
    eg
    0.05
    åħ·
    0.05
    rut
    0.05
    Activations Density 0.061%

    No Known Activations