© 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. 21083
    Prev
    Next
    INDEX
    Explanations

    degrees followed by C or F

    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
    à¹Ĭม
    -0.07
    лив
    -0.07
    orial
    -0.07
    ipur
    -0.07
    ê¼½
    -0.07
    VEST
    -0.06
    plain
    -0.06
    thinkable
    -0.06
    à¸Ļà¹Į
    -0.06
    ulihan
    -0.06
    POSITIVE LOGITS
    ity
    0.08
    rier
    0.06
    ÑģÑı
    0.06
    ÙħÙĥاÙĨ
    0.06
    enerate
    0.06
    áĥĶáĥ¡
    0.06
    sver
    0.06
     pauta
    0.06
    yek
    0.05
    osl
    0.05
    Activations Density 0.018%

    No Known Activations