© 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. 17360
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with fractions

    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
    ears
    -0.06
    миÑĢ
    -0.06
    ÅĤyn
    -0.06
    åħ®
    -0.06
    åĪ°å°¾
    -0.06
    лÑĸк
    -0.06
    entro
    -0.06
    inol
    -0.06
     wünsche
    -0.05
    æĽ´ç¾İ好
    -0.05
    POSITIVE LOGITS
    æĹł
    0.06
    “
    0.06
    ç³»
    0.06
    éļIJ
    0.05
    è§ģ
    0.05
    еÑĪ
    0.05
    è°¢
    0.05
    å½Ĵäºİ
    0.05
    禾
    0.05
    nen
    0.05
    Activations Density 0.008%

    No Known Activations