© 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. 22197
    Prev
    Next
    INDEX
    Explanations

    cell-like, neuron-like, function, acts, factor

    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
    ambre
    -0.08
    phe
    -0.07
    оÑĢÑĥ
    -0.07
    loat
    -0.06
    osten
    -0.06
    weet
    -0.06
    sza
    -0.06
    ÑģнÑĥ
    -0.06
    åŃIJæĽ°
    -0.06
    è°İ
    -0.06
    POSITIVE LOGITS
    åįģä¸Ģç«ł
    0.06
    ups
    0.05
     appropriate
    0.05
    ca
    0.05
    踪
    0.05
    низ
    0.05
    åħ¶ä¸»è¦ģ
    0.05
     organized
    0.05
     nl
    0.05
    -like
    0.05
    Activations Density 0.003%

    No Known Activations