© 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. 20486
    Prev
    Next
    INDEX
    Explanations

    attracts / attract

    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
     Dil
    -0.06
    avern
    -0.06
    çŁ³æ£ī
    -0.06
    abt
    -0.06
    ä¹Ŀå¹´
    -0.06
    alian
    -0.06
    agues
    -0.06
     constraint
    -0.05
    _constraint
    -0.05
    dil
    -0.05
    POSITIVE LOGITS
    åIJ¸å¼ķçĿĢ
    0.07
     attract
    0.06
     attracting
    0.06
    elin
    0.06
    饵
    0.06
     attracts
    0.06
    ucker
    0.06
     deco
    0.06
     attractive
    0.06
    åIJ¸å¼ķäºĨ
    0.06
    Activations Density 0.117%

    No Known Activations