© 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. 21082
    Prev
    Next
    INDEX
    Explanations

    continue reading

    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
    -0.06
    s
    -0.05
     ()
    -0.05
    å·§
    -0.05
    o
    -0.05
     _
    -0.05
    chio
    -0.05
    æľī为
    -0.05
    é
    -0.05
    one
    -0.05
    POSITIVE LOGITS
    ugel
    0.07
    kori
    0.07
    mails
    0.07
    èĤĨæĹłå¿Į
    0.07
    èĢģçļĦ
    0.07
    lesh
    0.07
    å·²ç»ĵæĿŁ
    0.07
    ecto
    0.07
     Horiz
    0.06
    lipp
    0.06
    Activations Density 0.001%

    No Known Activations