© 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. 19847
    Prev
    Next
    INDEX
    Explanations

    best, cross, size

    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
    èįĴåľ°
    -0.05
    ÙĪÛĮÛĮ
    -0.05
    éĹ²
    -0.05
    èĩªå·±æĥ³
    -0.05
    биÑĤ
    -0.05
    bsites
    -0.05
    å±ŀäºİèĩªå·±çļĦ
    -0.05
    æĹłæĢ¨
    -0.05
    POR
    -0.05
    /operator
    -0.05
    POSITIVE LOGITS
    conde
    0.06
    为æѤ
    0.06
    对æѤ
    0.06
    uç
    0.06
     lider
    0.06
    olicit
    0.06
     kit
    0.06
     pund
    0.06
    iazza
    0.06
    ocie
    0.06
    Activations Density 0.052%

    No Known Activations