© 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. 21350
    Prev
    Next
    INDEX
    Explanations

    concentrations, quantities, and doses

    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
    æ·±è¿ľ
    -0.05
     autant
    -0.05
    undert
    -0.05
    lien
    -0.05
    æłĩ
    -0.05
    åĪĨ享åĪ°
    -0.05
    ante
    -0.05
    ç¼Ńç»ķ
    -0.05
    -Smith
    -0.05
    è¿°
    -0.05
    POSITIVE LOGITS
    atform
    0.07
    äºİä¸Ģ
    0.06
    role
    0.06
    ç»Ŀ对ä¸įæĺ¯
    0.06
     pan
    0.06
    adat
    0.06
    responses
    0.06
    ä¸ij
    0.06
    URES
    0.06
    ukes
    0.06
    Activations Density 0.030%

    No Known Activations