© 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. 17449
    Prev
    Next
    INDEX
    Explanations

    ","])

    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§Ĺå§Ĺ
    -0.07
    gere
    -0.07
    еÑģÑĤв
    -0.07
     harinya
    -0.07
    çľŀ
    -0.07
     Gianni
    -0.07
    عÙĦÙĩ
    -0.07
    [âĢ¦
    -0.07
    ingly
    -0.07
    ationally
    -0.06
    POSITIVE LOGITS
    bl
    0.05
    å®Į
    0.05
     str
    0.05
     gl
    0.05
    Bl
    0.05
     al
    0.05
    ip
    0.05
     %
    0.04
     kh
    0.04
    éĤ£ä¸ĢåĪ»
    0.04
    Activations Density 0.001%

    No Known Activations