© 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. 21439
    Prev
    Next
    INDEX
    Explanations

    Jemaine

    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
    ätz
    -0.06
    ujan
    -0.05
     nests
    -0.05
    ondo
    -0.05
    clone
    -0.05
     overwhelm
    -0.05
     together
    -0.05
    feed
    -0.05
    _un
    -0.05
    edef
    -0.05
    POSITIVE LOGITS
    виков
    0.06
     parte
    0.06
    kadang
    0.05
     typeof
    0.05
    对åįİ
    0.05
    å¤ļå¤ļå°ij
    0.05
    รส
    0.05
     fil
    0.05
    éĵ¶
    0.05
    дено
    0.05
    Activations Density 0.003%

    No Known Activations