© 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. 17676
    Prev
    Next
    INDEX
    Explanations

    liquid crystal, data, Enum, Float, human

    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
    ansch
    -0.08
    SingleOrDefault
    -0.08
    skab
    -0.08
    说æľī
    -0.07
    ê´ĢìĹIJìĦľ
    -0.07
    ï¼ģ",
    -0.07
    posa
    -0.07
    evÅ¡ÃŃm
    -0.07
    áis
    -0.07
    incu
    -0.07
    POSITIVE LOGITS
    S
    0.05
    ces
    0.05
    è¿ĺæĺ¯
    0.05
    X
    0.05
    çħ§
    0.05
    D
    0.05
     h
    0.05
    w
    0.05
    åIJĮ
    0.04
    es
    0.04
    Activations Density 0.001%

    No Known Activations