© 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. 22538
    Prev
    Next
    INDEX
    Explanations

    Societies, kings, Saints, lengths, schemes, speeds

    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
    ACES
    -0.06
    ä¹ĭä¸ĢçļĦ
    -0.06
    issen
    -0.06
    eppe
    -0.06
     jeweils
    -0.06
    ç§ĭæľĪ
    -0.06
    pected
    -0.06
    eix
    -0.06
    wsze
    -0.05
    使çĶ¨åIJİ
    -0.05
    POSITIVE LOGITS
    æĸ°æŧ
    0.06
    æĢ§çļĦ
    0.06
    vom
    0.06
    om
    0.05
    гÑĭ
    0.05
    j
    0.05
    onor
    0.05
    er
    0.05
    ya
    0.05
    or
    0.05
    Activations Density 0.151%

    No Known Activations