© 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. 22535
    Prev
    Next
    INDEX
    Explanations

    .tif files

    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
    Negative Logits
    ัà¸ĩ
    -0.06
    ÑĦиÑı
    -0.05
     plaf
    -0.05
    ittal
    -0.05
    çķij
    -0.05
    iac
    -0.05
    ä¹İ
    -0.05
    act
    -0.05
    æľĢåIJİæĺ¯
    -0.05
    ]|
    -0.05
    POSITIVE LOGITS
    enders
    0.07
    ampa
    0.06
    ساÙĨÛĮ
    0.06
    -led
    0.06
    ãĤĦãĤĬ
    0.06
     confé
    0.06
    vince
    0.05
     decorr
    0.05
    åı¯èĥ½è¦ģ
    0.05
    andler
    0.05
    Activations Density 0.003%

    No Known Activations