© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19429
    Prev
    Next
    INDEX
    Explanations

    efficacy and effectiveness

    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
     dire
    -0.06
    äºijé£ŀ
    -0.05
    B
    -0.05
    E
    -0.05
    s
    -0.05
    ÑĭÑħ
    -0.05
    èĪ¬
    -0.05
    X
    -0.05
    7
    -0.05
     intended
    -0.05
    POSITIVE LOGITS
    +(\
    0.07
    Äįet
    0.06
    irut
    0.06
    Forge
    0.06
    fbe
    0.06
    utin
    0.06
     haus
    0.06
     пеÑĢео
    0.06
    ivr
    0.06
    ằng
    0.06
    Activations Density 0.018%

    No Known Activations