© 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. 18580
    Prev
    Next
    INDEX
    Explanations

    safety of

    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
    opl
    -0.05
    zelt
    -0.05
    heil
    -0.05
    è¿Īè¿Ľ
    -0.05
    stel
    -0.05
    æķ°æį®æĺ¾ç¤º
    -0.05
    æij§
    -0.04
    å¾Īä¸į
    -0.04
    æijĨåľ¨
    -0.04
     provided
    -0.04
    POSITIVE LOGITS
    inkin
    0.06
    ШÐIJ
    0.06
    ä»Ģ
    0.06
    è¾ĸ
    0.06
    åıĹçIJĨåIJİ
    0.06
    วà¸Ļ
    0.06
     abbr
    0.06
    æľĪåı·
    0.06
    atches
    0.06
    nb
    0.06
    Activations Density 0.005%

    No Known Activations