© 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. 20371
    Prev
    Next
    INDEX
    Explanations

    great and positive evaluations

    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
    æijĬ
    -0.05
    代表çļĦ
    -0.05
    et
    -0.05
    riend
    -0.05
    AT
    -0.05
    åį¡æĭī
    -0.05
     знаÑĩи
    -0.05
    代表
    -0.05
     an
    -0.05
    friend
    -0.05
    POSITIVE LOGITS
    essant
    0.07
     conferir
    0.06
    Prefs
    0.06
    akar
    0.06
    ÙĪÙĨÙĬ
    0.06
    nic
    0.06
     dosp
    0.06
    ikki
    0.06
    ingly
    0.05
    ved
    0.05
    Activations Density 0.002%

    No Known Activations