© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19924
    Prev
    Next
    INDEX
    Explanations

    real, hands, lives, course, applications, children, market

    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
    cach
    -0.07
    inhos
    -0.07
    aten
    -0.06
    chand
    -0.06
    ftar
    -0.06
    icali
    -0.06
    ç«ĭãģ¡
    -0.06
    jac
    -0.06
    à¸ŀà¸Ń
    -0.06
    aghan
    -0.06
    POSITIVE LOGITS
    '
    0.06
    ing
    0.05
    å¿ħ
    0.05
    ä¹ĭæīĢ以
    0.05
    å¾Ĺ
    0.05
    ÑĮ
    0.05
    åĽ°
    0.05
    `
    0.05
    Ñĥв
    0.05
     de
    0.05
    Activations Density 0.078%

    No Known Activations