© 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. 18539
    Prev
    Next
    INDEX
    Explanations

    summary or description

    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
    er
    -0.08
    aster
    -0.06
    åĸĭ
    -0.05
    ATURE
    -0.05
    aoke
    -0.05
    dou
    -0.05
    ature
    -0.05
    der
    -0.05
    eking
    -0.05
    bra
    -0.05
    POSITIVE LOGITS
    ulia
    0.06
    illons
    0.05
    ãģ«ãģĶ缸è«ĩ
    0.05
    éĻ¤
    0.05
    对çĻ½
    0.05
    esity
    0.05
    Å¡Äį
    0.05
    ril
    0.05
    ä¸ĭåIJĮ
    0.05
    éĻ¤åİ»
    0.05
    Activations Density 0.015%

    No Known Activations