© 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. 17412
    Prev
    Next
    INDEX
    Explanations

    numbers following one

    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
    s
    -0.06
    äºĽ
    -0.06
    e
    -0.06
    ed
    -0.05
    aug
    -0.05
    ic
    -0.05
    <
    -0.05
    Ãło
    -0.05
    ono
    -0.05
    uch
    -0.05
    POSITIVE LOGITS
    eluk
    0.07
     éner
    0.07
    ìĶ©
    0.07
    usan
    0.07
     mainScreen
    0.07
     kalinya
    0.06
     вниманиÑİ
    0.06
    Ñģнабжение
    0.06
     ìĭ¶ìĸ´
    0.06
    nal
    0.06
    Activations Density 0.043%

    No Known Activations