© 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. 17820
    Prev
    Next
    INDEX
    Explanations

    am, is, was, cannot, that

    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
    ÑĨ
    -0.07
    з
    -0.06
    (
    -0.06
    åıªè§ģ
    -0.05
     out
    -0.05
    zal
    -0.05
    init
    -0.05
    oop
    -0.05
    ÑĢ
    -0.05
    oint
    -0.05
    POSITIVE LOGITS
    ×Ļר×Ļ×Ŀ
    0.07
    atra
    0.06
    ãĤ·ãĥ³ãĤ°
    0.06
     strane
    0.06
    imed
    0.06
    è¿ĺåĸľæ¬¢
    0.06
    ÑģÑģоÑĢа
    0.06
    ":"'
    0.06
    ÙĨداÙĨ
    0.06
     ÙĦÙĦÙħرة
    0.06
    Activations Density 0.024%

    No Known Activations