© 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. 21999
    Prev
    Next
    INDEX
    Explanations

    evaluation and punctuation

    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
    ipu
    -0.06
    é£İåı£
    -0.06
    fik
    -0.06
    æ½®
    -0.06
    æĿ¾
    -0.05
    antik
    -0.05
    åĬĪ
    -0.05
    æīĵæ°´
    -0.05
    èļĮ
    -0.05
    appropri
    -0.05
    POSITIVE LOGITS
    otov
    0.07
    rição
    0.06
    itaire
    0.05
     ...\
    0.05
    ÑĢаÑĤоÑĢ
    0.05
     ..."
    0.05
     bios
    0.05
    ().'
    0.05
     negoz
    0.05
    Ùģاض
    0.05
    Activations Density 0.004%

    No Known Activations