© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19231
    Prev
    Next
    INDEX
    Explanations

    your, you

    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
    новиÑĩ
    -0.06
     Ving
    -0.06
     صادر
    -0.06
    asury
    -0.06
    ạ
    -0.06
    áros
    -0.06
    мÑıн
    -0.06
    lada
    -0.06
     fungs
    -0.06
    éĹ·
    -0.06
    POSITIVE LOGITS
    并举
    0.05
    ç¤
    0.05
    ä
    0.05
    áĥ£áĥłáĥĺ
    0.05
    enske
    0.05
    egner
    0.05
    審
    0.05
    ën
    0.05
     der
    0.04
    OCI
    0.04
    Activations Density 0.001%

    No Known Activations