© 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. 21257
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and auxiliaries

    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
    uoti
    -0.07
    uvi
    -0.06
    ofil
    -0.06
    rof
    -0.06
    ÑĢÑİ
    -0.06
    endi
    -0.06
    à¸ŀิà¸ģาร
    -0.06
    awai
    -0.05
    entic
    -0.05
     Pró
    -0.05
    POSITIVE LOGITS
    ÏĢε
    0.06
    æĽ´ä½ķåĨµ
    0.05
    æĬĺ
    0.05
    ä½ķåĨµ
    0.05
    çĪ¬
    0.05
    举ä¸Ģåıįä¸ī
    0.05
    ivre
    0.05
     rep
    0.05
    _stop
    0.05
    ér
    0.05
    Activations Density 0.075%

    No Known Activations