© 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. 17501
    Prev
    Next
    INDEX
    Explanations

    X or not

    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
    άÏĤ
    -0.07
    edly
    -0.07
    ấc
    -0.07
    ague
    -0.07
    icano
    -0.07
    bull
    -0.07
    ä¸Ńä¸ĵ
    -0.06
    ÑĩеÑĢа
    -0.06
    èĢĮéĻį
    -0.06
    ilas
    -0.06
    POSITIVE LOGITS
    شاÙĨ
    0.06
     really
    0.05
    en
    0.05
    par
    0.05
    ïn
    0.05
    л
    0.05
    entr
    0.05
     samt
    0.04
    åıįè¿ĩæĿ¥
    0.04
    åľ¨éĤ£
    0.04
    Activations Density 0.008%

    No Known Activations