© 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. 20925
    Prev
    Next
    INDEX
    Explanations

    subjects following the

    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
    oud
    -0.06
    ure
    -0.05
     one
    -0.05
    UR
    -0.05
     SarÃł
    -0.05
    se
    -0.05
     our
    -0.05
    ur
    -0.05
     whether
    -0.05
    lah
    -0.05
    POSITIVE LOGITS
    endar
    0.07
    çļĦåı«
    0.06
    æľĢéļ¾
    0.06
    atlan
    0.06
    IANA
    0.06
    -END
    0.06
    ziÄĻki
    0.06
    ciÄĻ
    0.06
    òm
    0.06
    äºĨæķ´ä¸ª
    0.06
    Activations Density 0.091%

    No Known Activations