© 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. 16561
    Prev
    Next
    INDEX
    Explanations

    topic followed by descriptor

    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
    estos
    -0.06
    åħĭåħ°
    -0.06
    å¿ħè¦ģçļĦ
    -0.06
    atson
    -0.06
    åIJĮæĹ¶åľ¨
    -0.06
    relev
    -0.06
    éĢłæĪIJå½±åĵį
    -0.06
    “To
    -0.06
    illet
    -0.06
    arez
    -0.06
    POSITIVE LOGITS
    纳德
    0.06
    æ¦Ĥè¿°
    0.05
    ÙıÙĦ
    0.05
    人åķĬ
    0.05
    vin
    0.05
    ׼×ķ
    0.05
     Planner
    0.05
    çļĦéĤ£äºĽ
    0.05
     particularly
    0.05
    éĩĮåħĭ
    0.05
    Activations Density 0.053%

    No Known Activations