© 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. 17224
    Prev
    Next
    INDEX
    Explanations

    `following code`

    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¿ħè¦ģ
    -0.07
    å¿ħè¦ģçļĦ
    -0.07
     necessary
    -0.06
    lation
    -0.06
    кÑĢа
    -0.05
    Ø·ÙĨ
    -0.05
    essional
    -0.05
    repub
    -0.05
    åĺĪ
    -0.05
    NEL
    -0.05
    POSITIVE LOGITS
    iau
    0.06
    ivity
    0.06
    度çļĦ
    0.05
    ÑĤеÑĢÑı
    0.05
    uire
    0.05
    æŀģäºĨ
    0.05
    ÑģÑı
    0.05
    ress
    0.05
    erein
    0.05
    archy
    0.05
    Activations Density 0.008%

    No Known Activations