© 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. 18670
    Prev
    Next
    INDEX
    Explanations

    space station and ISS

    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
    家éŨ
    -0.06
    omo
    -0.05
     pits
    -0.05
    horn
    -0.05
    åħ¬å¢ĵ
    -0.05
     sealed
    -0.05
    åľ°å¹³
    -0.05
    rowned
    -0.05
    æŃ¢æŃ¥
    -0.05
     history
    -0.05
    POSITIVE LOGITS
    åIJĪ
    0.06
    æĵ¦æ´Ĺ
    0.06
    ÑģÑĤавлÑıеÑĤ
    0.06
    æIJŃ
    0.06
    rah
    0.06
    fus
    0.06
    æ¼Ĥ
    0.06
    isman
    0.06
    chow
    0.06
    ilst
    0.05
    Activations Density 0.009%

    No Known Activations