© 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. 20077
    Prev
    Next
    INDEX
    Explanations

    possible outcomes or qualities

    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
    ÑĢек
    -0.06
     peine
    -0.05
    els
    -0.05
     sometimes
    -0.05
    ÑĢед
    -0.05
    æĹ¶ä»£
    -0.05
    æĹ¶ä»£çļĦ
    -0.05
    ÙĨد
    -0.05
     поÑĢой
    -0.05
    lej
    -0.05
    POSITIVE LOGITS
    alization
    0.05
    inflam
    0.05
    alisation
    0.05
     Hoh
    0.05
    utures
    0.05
    sa
    0.05
    cko
    0.05
    saus
    0.05
    cha
    0.05
    ä¸ī级
    0.05
    Activations Density 0.044%

    No Known Activations