© 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. 18529
    Prev
    Next
    INDEX
    Explanations

    file formats and data types

    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
    人éģĵ
    -0.06
    iah
    -0.06
    èĭ¥æĹł
    -0.06
    irc
    -0.05
    gh
    -0.05
    abin
    -0.05
    è²Į
    -0.05
    å¦Ĥæŀľæ²¡æľī
    -0.05
    quoise
    -0.05
    Ī
    -0.05
    POSITIVE LOGITS
    erness
    0.07
    andle
    0.06
    ernt
    0.06
    ocity
    0.06
    dor
    0.06
    бла
    0.06
    å½Ĵå±ŀäºİä¸Ĭå¸Ĥåħ¬åı¸
    0.05
    ستÙĩ
    0.05
    çĶ¨å¿ĥåİ»
    0.05
    æĶ¶èİ·çļĦ
    0.05
    Activations Density 0.028%

    No Known Activations