© 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. 17230
    Prev
    Next
    INDEX
    Explanations

    type declarations

    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
    clusive
    -0.06
    rut
    -0.05
    apis
    -0.05
    es
    -0.05
    泡
    -0.05
    ayu
    -0.05
    xE
    -0.05
    ight
    -0.05
    =:
    -0.05
    izes
    -0.05
    POSITIVE LOGITS
    icarakan
    0.06
    IKA
    0.06
    ëĿ¼ë©´
    0.05
    iog
    0.05
    à¸Ń
    0.05
    çĽ¸å¯¹
    0.05
    _RATIO
    0.05
    ä»ĸ们对
    0.05
    åĪĺæµ·
    0.05
     Hogan
    0.05
    Activations Density 0.013%

    No Known Activations