© 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. 21588
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    éĢ»
    -0.07
    EFE
    -0.06
    åĽ½åĬĽ
    -0.06
    ÑģÑĤоÑĢо
    -0.06
    åĨµ
    -0.06
    ä¿¡æģ¯çĶ±
    -0.06
    è¿Ļä¸ĸä¸Ĭ
    -0.06
    endorf
    -0.06
    ½
    -0.05
    attro
    -0.05
    POSITIVE LOGITS
    uren
    0.06
    hood
    0.06
    encias
    0.05
    aus
    0.05
    ars
    0.05
    ä¸Ģçľ¼
    0.05
    Containing
    0.05
    çī¹æ®ĬæĢ§
    0.05
    èİİ
    0.05
    eer
    0.05
    Activations Density 0.078%

    No Known Activations