© 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. 21974
    Prev
    Next
    INDEX
    Explanations

    gene, genetics, biological functions

    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
    oms
    -0.05
    åľº
    -0.05
    è§ĦèĮĥè¦ģæ±Ĥ
    -0.05
    Gui
    -0.05
    ó
    -0.05
    uzz
    -0.05
    orth
    -0.05
    çŃīä¸įåIJĮ
    -0.05
    ظ
    -0.05
    åł´
    -0.05
    POSITIVE LOGITS
    agen
    0.07
    ÐĵлавнÑĭе
    0.06
     '<%=
    0.06
    iede
    0.06
    交åĩº
    0.06
    uellen
    0.06
    iaux
    0.06
    æŃ²æľĪ
    0.06
     colectiv
    0.06
    reten
    0.06
    Activations Density 0.001%

    No Known Activations