© 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. 21836
    Prev
    Next
    INDEX
    Explanations

    names of fields, claims

    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
    å»ī
    -0.05
     before
    -0.05
    Õ²
    -0.05
    m
    -0.05
    V
    -0.05
     closely
    -0.05
    æ±Ĥæĺ¯
    -0.04
     Everything
    -0.04
     as
    -0.04
    n
    -0.04
    POSITIVE LOGITS
    ä¸įåIJĮæŶ
    0.06
    ëĸ»
    0.06
    ryp
    0.06
    äºijçļĦ
    0.06
    iture
    0.06
    reserve
    0.06
     conscientes
    0.06
     Merk
    0.06
    ries
    0.06
    RIES
    0.06
    Activations Density 0.009%

    No Known Activations