© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18989
    Prev
    Next
    INDEX
    Explanations

    lead or acid

    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
    illi
    -0.06
    ingen
    -0.06
    orp
    -0.06
    çļĦåİŁåĽłä¹ĭä¸Ģ
    -0.06
    Ing
    -0.06
    ä¸įåıij
    -0.05
    appendTo
    -0.05
    è´¹æŶ
    -0.05
    æĺ¯ä¸º
    -0.05
    æİĽãģij
    -0.05
    POSITIVE LOGITS
    ly
    0.06
    ame
    0.06
     tendency
    0.06
     detection
    0.05
    ir
    0.05
    éĹ¹
    0.05
    leit
    0.05
    jev
    0.05
    owl
    0.05
    s
    0.05
    Activations Density 0.009%

    No Known Activations