© 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. 20996
    Prev
    Next
    INDEX
    Explanations

    type

    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
     chains
    -0.06
     Chain
    -0.06
    à¹Ģยีà¹Īยมà¸Ĭม
    -0.05
    çľī
    -0.05
    éĺ¶æ®µ
    -0.05
    æĢ»ä¸įèĥ½
    -0.05
     chain
    -0.05
     converting
    -0.05
    ฮิà¸ķ
    -0.05
    ernet
    -0.05
    POSITIVE LOGITS
    åĴĮå¤ļ
    0.06
    ë¡Ģ
    0.05
    çľ¾
    0.05
    ling
    0.05
    æĪĸå¤ļ
    0.05
    anc
    0.05
    ilingual
    0.05
    زÙĦ
    0.05
    пле
    0.05
     Ñģозн
    0.05
    Activations Density 0.092%

    No Known Activations