© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19637
    Prev
    Next
    INDEX
    Explanations

    cursor, Sprite, Button, Remove

    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
    одо
    -0.05
     menc
    -0.05
     Minor
    -0.05
    omatis
    -0.05
     es
    -0.05
    äºĴ
    -0.04
    à¸Ľà¸£à¸°
    -0.04
    ARS
    -0.04
     bur
    -0.04
    oc
    -0.04
    POSITIVE LOGITS
    heur
    0.06
    leih
    0.06
    жели
    0.06
    verka
    0.06
    lettere
    0.06
    ryw
    0.06
    ellone
    0.06
     Bombe
    0.06
    ciano
    0.06
    unan
    0.06
    Activations Density 0.002%

    No Known Activations