© 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. 16843
    Prev
    Next
    INDEX
    Explanations

    ligament

    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
    amo
    -0.05
     ru
    -0.05
    èľ
    -0.05
     Org
    -0.05
    orr
    -0.05
    omo
    -0.05
    大çļĦ
    -0.05
    rific
    -0.05
    ruc
    -0.05
    è§ĦèĮĥæĢ§
    -0.05
    POSITIVE LOGITS
    blig
    0.06
    éļıçĿĢæŶéĹ´çļĦæݨ移
    0.06
     каÑĢÑĤи
    0.06
    åĥļ
    0.06
    _INCLUDE
    0.06
    -counter
    0.06
     olsun
    0.06
     vertre
    0.06
     اÙĦØ´Ùħ
    0.06
    iments
    0.05
    Activations Density 0.007%

    No Known Activations