© 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. 18446
    Prev
    Next
    INDEX
    Explanations

    forces of evil, dark side, unleashed

    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
    itr
    -0.05
    æīĵæİī
    -0.05
    iol
    -0.05
     Revolutionary
    -0.05
    åģļ为
    -0.05
     ose
    -0.05
    ulin
    -0.05
    6
    -0.05
     Hess
    -0.05
     hypoc
    -0.04
    POSITIVE LOGITS
    woch
    0.07
    waan
    0.07
    èĶĵ延
    0.06
    estin
    0.06
    Cas
    0.06
    cas
    0.06
     lì
    0.06
    ispers
    0.06
    ewan
    0.06
    éĥ½æĽ¾
    0.06
    Activations Density 0.004%

    No Known Activations