© 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. 20306
    Prev
    Next
    INDEX
    Explanations

    AFTER INSERT, UPDATE, CREATE TRIGGER

    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
     A
    -0.06
    ilh
    -0.05
    heiten
    -0.05
     power
    -0.05
    à¶ļ
    -0.05
    èĽŁ
    -0.05
    Ñħин
    -0.04
    对çħ§
    -0.04
    amil
    -0.04
    urrencies
    -0.04
    POSITIVE LOGITS
     Keys
    0.06
     fro
    0.06
    以ä¸ĭæŃ¥éª¤
    0.06
    ÑģиÑħо
    0.06
    æĪijçļĦä¼ģä¸ļ
    0.06
    bet
    0.06
    ousy
    0.05
     travers
    0.05
    usable
    0.05
    å¯ĨåĪĩæݥ触
    0.05
    Activations Density 0.016%

    No Known Activations