© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19519
    Prev
    Next
    INDEX
    Explanations

    code that takes

    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
    akup
    -0.06
    ãĤĴãģĭãģij
    -0.06
     erb
    -0.06
    ï¸İ
    -0.06
    inÄĻ
    -0.06
     Zot
    -0.06
    annuncio
    -0.06
    olated
    -0.06
    CLUDING
    -0.06
    smith
    -0.06
    POSITIVE LOGITS
    hir
    0.06
    emp
    0.06
    avn
    0.06
    çŃĭ
    0.06
    æį
    0.05
    yll
    0.05
    è½
    0.05
    ../../../
    0.05
     strat
    0.05
    åĽ½äº§
    0.05
    Activations Density 0.051%

    No Known Activations