© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21643
    Prev
    Next
    INDEX
    Explanations

    reading 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
    Not in Any Lists

    No Comments

    Negative Logits
    åħijç¾İåħĥ
    -0.06
    è²Į
    -0.06
     coup
    -0.06
    åºľçļĦ
    -0.05
     haste
    -0.05
    稽
    -0.05
    Skeleton
    -0.05
    ç»ıæµİåıijå±ķçļĦ
    -0.05
    ILLA
    -0.05
    Fold
    -0.05
    POSITIVE LOGITS
    ars
    0.06
     into
    0.06
    ulating
    0.06
    ing
    0.06
    uÅĤ
    0.05
    ming
    0.05
    /false
    0.05
    os
    0.05
    amis
    0.05
    breaking
    0.05
    Activations Density 0.009%

    No Known Activations