© 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. 21170
    Prev
    Next
    INDEX
    Explanations

    statement

    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
    iously
    -0.06
    -0.05
    -0.05
    ç¦Ģ
    -0.05
    åħī
    -0.05
     convenient
    -0.05
     -
    -0.05
     (
    -0.05
    kadang
    -0.05
    unque
    -0.05
    POSITIVE LOGITS
    ever
    0.08
    azon
    0.08
    skraft
    0.08
     Afinal
    0.07
     Ðijлаго
    0.07
    amedi
    0.07
    atology
    0.07
     darb
    0.07
    ÙĤرÙĬر
    0.07
    ÑĢаво
    0.07
    Activations Density 0.012%

    No Known Activations