© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21879
    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
    建ç«ĭåľ¨
    -0.06
    med
    -0.05
    ox
    -0.05
    æī
    -0.05
    pm
    -0.05
     "
    -0.05
    çĭ¬åĪĽ
    -0.05
    rame
    -0.05
    mb
    -0.05
    LENGTH
    -0.04
    POSITIVE LOGITS
    enek
    0.07
    istán
    0.07
    ancier
    0.06
    /place
    0.06
     sclerosis
    0.06
    ystate
    0.06
    åı¯ä»¥æĶ¾å¿ĥ
    0.06
    tright
    0.06
    valg
    0.06
    ioen
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.