© 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. 22260
    Prev
    Next
    INDEX
    Explanations

    lamb dish

    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
    ä¿
    -0.07
    oter
    -0.07
    iania
    -0.06
     Terb
    -0.06
    ÙĪائ
    -0.06
    بÙĬض
    -0.06
    urator
    -0.06
    æ¨Ļæºĸ
    -0.06
    udd
    -0.06
    elé
    -0.06
    POSITIVE LOGITS
     heavy
    0.05
    并éĩį
    0.05
    -uppercase
    0.05
    mate
    0.05
     fine
    0.05
    ahir
    0.05
    fang
    0.05
     bellissima
    0.05
     chosen
    0.05
    ีย
    0.05
    Activations Density 0.023%

    No Known Activations