© 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. 21636
    Prev
    Next
    INDEX
    Explanations

    texture sampler bitmap sprite

    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
    åĴĮä¿¡æģ¯åĮĸ
    -0.06
    enville
    -0.06
     dehydration
    -0.05
    pend
    -0.05
    å¡ŀ
    -0.05
    oplast
    -0.05
    å±ı
    -0.05
    uste
    -0.05
    ä»¥ä¹łè¿ijå¹³
    -0.05
    è´
    -0.05
    POSITIVE LOGITS
    wis
    0.06
    ken
    0.06
     thâm
    0.06
    æĦŁè§īå¾Ī
    0.05
    æ±²
    0.05
    ç»ĵå©ļè¯ģ
    0.05
    inne
    0.05
    績
    0.05
    ksi
    0.05
     stri
    0.05
    Activations Density 0.020%

    No Known Activations