© 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. 18445
    Prev
    Next
    INDEX
    Explanations

    numbered lists or bullet points

    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
    æĢĿ
    -0.05
    vend
    -0.05
     roup
    -0.05
    åħ¶ä¸Ń
    -0.05
    bras
    -0.05
    ç³»
    -0.05
    èĦijåŃIJéĩĮ
    -0.05
    ühl
    -0.04
     lind
    -0.04
    صرÙĬ
    -0.04
    POSITIVE LOGITS
    apor
    0.07
    etheless
    0.06
    tku
    0.06
    æĶ¿çŃĸ解读
    0.06
    бе
    0.06
     Cuomo
    0.06
    çĦķçĦ¶
    0.06
    ï¼ĮãĢĬ
    0.06
    æĶ¿åºľåħ¬åijĬ
    0.06
    ubro
    0.06
    Activations Density 0.028%

    No Known Activations