© 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. 22294
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ¸
    -0.07
    owns
    -0.07
    borne
    -0.06
    resa
    -0.06
    :description
    -0.06
    å®Ľ
    -0.06
    çľł
    -0.06
    otten
    -0.06
    feeding
    -0.06
     Kort
    -0.06
    POSITIVE LOGITS
     leh
    0.05
    ardon
    0.05
     floor
    0.05
    _ps
    0.05
     Name
    0.05
    ÈĽe
    0.05
    å±ĤéĿ¢ä¸Ĭ
    0.05
    _/
    0.05
    éĶĭ
    0.04
     tough
    0.04
    Activations Density 0.000%

    No Known Activations