© 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. 18290
    Prev
    Next
    INDEX
    Explanations

    comic book titles

    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
    å¾Ĵ
    -0.06
    hoff
    -0.06
     polynomial
    -0.06
     patent
    -0.05
    软件èijĹä½ľæĿĥ
    -0.05
    åĪĨæ°´
    -0.05
    ella
    -0.05
    å®ĺåħµ
    -0.05
    omp
    -0.05
     warming
    -0.05
    POSITIVE LOGITS
    лин
    0.06
    UPS
    0.06
    annel
    0.06
     UPS
    0.06
    åĮ£
    0.06
    åĴ«
    0.06
    éģ®èĶ½
    0.06
     Papel
    0.06
    groupName
    0.06
    rolley
    0.06
    Activations Density 0.036%

    No Known Activations