© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20381
    Prev
    Next
    INDEX
    Explanations

    been followed by descriptive adjectives

    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
    ÑģÑı
    -0.07
    able
    -0.06
    1
    -0.06
    Q
    -0.06
    \
    -0.06
    ors
    -0.06
    2
    -0.06
    W
    -0.05
    iz
    -0.05
    Z
    -0.05
    POSITIVE LOGITS
    elv
    0.07
    edar
    0.07
    bir
    0.07
    ená
    0.06
    uszcz
    0.06
    yip
    0.06
    itamente
    0.06
    ãģıãĤĬ
    0.06
    rific
    0.06
    eni
    0.06
    Activations Density 0.010%

    No Known Activations