© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22272
    Prev
    Next
    INDEX
    Explanations

    hardware components or equipment

    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
    éĢĨ
    -0.07
    yd
    -0.06
    mien
    -0.06
    éĢĨæµģ
    -0.06
    缼
    -0.06
    æ½ľ
    -0.06
    éĢĨåIJij
    -0.06
    è°ĥ
    -0.06
    omod
    -0.05
    ìĹŃ
    -0.05
    POSITIVE LOGITS
     ver
    0.06
    Hardware
    0.05
    å®ŀä½ĵ
    0.05
     liá»ĩt
    0.05
    ä½ķåľ¨
    0.05
     hardware
    0.05
     Hardware
    0.05
    emen
    0.05
    chten
    0.05
    ]bool
    0.05
    Activations Density 0.004%

    No Known Activations