© 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. 19064
    Prev
    Next
    INDEX
    Explanations

    code identifiers and errors

    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
    lob
    -0.06
    åħģ
    -0.06
    ìĨ¡
    -0.05
    gaard
    -0.05
    æĥ³è¦ģ
    -0.05
    æĢ»çļĦ
    -0.05
    nore
    -0.05
    å¸ĮæľĽ
    -0.05
    æĢ
    -0.05
    è¶Ĭ
    -0.05
    POSITIVE LOGITS
    taus
    0.06
    èī³éĺ³
    0.06
    emark
    0.06
    eful
    0.06
     similarly
    0.06
    ÙĤØ©
    0.06
    ÑģÑĤаÑĤи
    0.06
    acu
    0.06
    viso
    0.06
    她ä¼ļ
    0.06
    Activations Density 0.003%

    No Known Activations