© 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. 21663
    Prev
    Next
    INDEX
    Explanations

    Eurema, Kaisa, Prettl, Jexus, Sua, Penna, Reba

    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
     sign
    -0.05
     of
    -0.05
    bery
    -0.05
     smooth
    -0.05
    sab
    -0.05
    olec
    -0.05
     sh
    -0.05
    æĸ½å·¥è¿ĩç¨ĭä¸Ń
    -0.05
    heit
    -0.05
    heiten
    -0.05
    POSITIVE LOGITS
    yczy
    0.07
    isinya
    0.07
    ampoo
    0.06
    ctl
    0.06
    иÑģÑĤÑĢи
    0.06
    hadap
    0.06
    _compat
    0.06
     Zoals
    0.06
     baratos
    0.06
    æĪijçļĦçľĭæ³ķ
    0.06
    Activations Density 0.005%

    No Known Activations