© 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. 17880
    Prev
    Next
    INDEX
    Explanations

    hurricane followed by names

    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
    ç«ĭæĸ°
    -0.06
    ç¥ĸåħĪ
    -0.05
    comp
    -0.05
    ä¸Ĭåĵģ
    -0.05
     Paolo
    -0.05
    alti
    -0.05
    oki
    -0.05
    åħ¨çIJĥåĮĸ
    -0.05
    å¤ļåĩº
    -0.05
    imei
    -0.05
    POSITIVE LOGITS
    ä¿¡å°ģ
    0.07
    åĬ²
    0.07
    åĬ²åĦ¿
    0.06
     hort
    0.06
    纨
    0.06
    -envelope
    0.06
    atif
    0.06
    çģ¿
    0.06
    绩
    0.06
    æĹĭ
    0.06
    Activations Density 0.014%

    No Known Activations