© 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. 21941
    Prev
    Next
    INDEX
    Explanations

    mark

    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
    veil
    -0.06
    rous
    -0.06
    èĬ¦
    -0.06
    ried
    -0.05
    rippling
    -0.05
    è¿ĩåİ»çļĦ
    -0.05
    à¦ŀà§įà¦ļ
    -0.05
    hid
    -0.05
    æĥłåıĬ
    -0.05
     cellspacing
    -0.05
    POSITIVE LOGITS
    ç»Īç»ĵ
    0.07
    ascal
    0.06
     missions
    0.06
     Burnett
    0.06
    agal
    0.06
    åIJİç«ĭåį³
    0.06
    å±Ī
    0.06
     utr
    0.06
    qid
    0.06
    éĹŃåIJĪ
    0.05
    Activations Density 0.008%

    No Known Activations