© 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. 20835
    Prev
    Next
    INDEX
    Explanations

    calculating factors and divisors

    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
    عار
    -0.06
    æī¿åĬŀåįķä½į
    -0.05
    duto
    -0.05
     monet
    -0.05
     kij
    -0.05
    åĪ©çĶ¨èĢħ
    -0.05
     Nimbus
    -0.05
    odia
    -0.05
    Former
    -0.05
    auf
    -0.05
    POSITIVE LOGITS
    -like
    0.05
    style
    0.05
    ness
    0.05
    éĢļè¿ĩ以ä¸Ĭ
    0.05
    boy
    0.05
    çīĪæľ¬
    0.05
    ç·£
    0.05
     herstellen
    0.05
    ž
    0.05
    acy
    0.05
    Activations Density 0.001%

    No Known Activations