© 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. 20233
    Prev
    Next
    INDEX
    Explanations

    NSFW

    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
    orden
    -0.06
     Velo
    -0.06
    fällig
    -0.06
    åIJįçīĩ
    -0.06
    formats
    -0.06
    plin
    -0.06
     rightly
    -0.06
     Köl
    -0.06
     poised
    -0.06
     silenci
    -0.06
    POSITIVE LOGITS
    ness
    0.08
    ä¸Ģæĥ³åĪ°
    0.05
    åľ°é»Ħ
    0.05
    çĥĺ
    0.05
    [
    0.05
    .security
    0.05
    ä¹IJåĽŃ
    0.05
    æ¦Ĥ
    0.05
    ÑİÑĤ
    0.05
    ting
    0.05
    Activations Density 0.001%

    No Known Activations