© 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. 18079
    Prev
    Next
    INDEX
    Explanations

    between, inequality, tables

    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
    em
    -0.05
    çij
    -0.05
    ham
    -0.05
    ï
    -0.05
    cele
    -0.05
    ä¸įæľį
    -0.05
    aps
    -0.05
     Valley
    -0.05
     approximate
    -0.05
    лиÑĩнÑĭй
    -0.05
    POSITIVE LOGITS
     **:**
    0.07
     therefore
    0.06
     ofre
    0.06
    niÄį
    0.06
    ÑĨеÑĢ
    0.06
    znak
    0.06
     tehát
    0.06
    ectiv
    0.06
    ezer
    0.06
    æİ§ç³»ç»Ł
    0.06
    Activations Density 0.003%

    No Known Activations