© 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. 21036
    Prev
    Next
    INDEX
    Explanations

    align with goals or business

    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
    å©¿
    -0.06
    enheim
    -0.06
    uhnya
    -0.06
    iato
    -0.05
    matic
    -0.05
    iator
    -0.05
    iates
    -0.05
    è¦ģåľ¨
    -0.05
    rof
    -0.05
    åİĨæŶ
    -0.05
    POSITIVE LOGITS
    éral
    0.07
    hed
    0.07
    ä½Ļ人次
    0.06
    egang
    0.06
     ủng
    0.06
    ebak
    0.06
    halt
    0.06
    ondre
    0.06
    awal
    0.06
    egi
    0.06
    Activations Density 0.009%

    No Known Activations