© 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. 16855
    Prev
    Next
    INDEX
    Explanations

    skirt

    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
    orgeous
    -0.07
    rescia
    -0.07
    Ư
    -0.06
    ijnen
    -0.06
    lius
    -0.06
    åıĤéĺħ
    -0.06
    ISTER
    -0.06
    ìĦĿ
    -0.06
    ä¸Ģ个åı«
    -0.06
    æ¿ģ
    -0.06
    POSITIVE LOGITS
    åģ¥åº·çļĦ
    0.06
    orsa
    0.06
    s
    0.05
    o
    0.05
    åIJĪãģĦ
    0.05
     hereby
    0.05
     balances
    0.05
    alas
    0.05
    urs
    0.05
     Tracks
    0.05
    Activations Density 0.001%

    No Known Activations