© 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. 21951
    Prev
    Next
    INDEX
    Explanations

    asking for information

    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
    ç«ĭ
    -0.05
    ste
    -0.05
    εί
    -0.05
    ney
    -0.05
    è·º
    -0.05
     liv
    -0.05
    retry
    -0.05
    ilih
    -0.05
    б
    -0.05
     d
    -0.05
    POSITIVE LOGITS
    åIJĥå®ĮäºĨ
    0.06
    缮çļĦæĺ¯
    0.06
    ваннÑĭ
    0.06
     Nations
    0.06
     subsequent
    0.06
    ÑĤномÑĥ
    0.06
    itats
    0.06
     samot
    0.06
    unken
    0.06
     Management
    0.06
    Activations Density 0.004%

    No Known Activations