© 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. 20495
    Prev
    Next
    INDEX
    Explanations

    .com links

    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
    ÃŃnu
    -0.06
    eb
    -0.06
    blem
    -0.06
    ÑĥлÑĮÑĤ
    -0.06
     ÙħÙħ
    -0.05
    resse
    -0.05
    anee
    -0.05
     unreachable
    -0.05
    Born
    -0.05
    éļ¾åħį
    -0.05
    POSITIVE LOGITS
    ÑĪÑĤ
    0.05
    ihan
    0.05
    ìĭĿìľ¼ë¡ľ
    0.05
    opcion
    0.05
    ä¼łåªĴ
    0.05
    igen
    0.05
     shit
    0.05
    ç½®æį¢
    0.05
    ifty
    0.05
    çļ®
    0.05
    Activations Density 0.007%

    No Known Activations