© 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. 20453
    Prev
    Next
    INDEX
    Explanations

    soul, room, away, retreat

    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
    æľīå¾Īå¤ļ
    -0.08
     ðŁĺĢ
    -0.08
    æľīä¸ĢäºĽ
    -0.08
    éĿŀ常éĩįè¦ģçļĦ
    -0.07
    eeee
    -0.07
     horrible
    -0.07
     messed
    -0.07
    EEEE
    -0.07
    ðŁĺĢ
    -0.07
    èµ·äºĨ
    -0.07
    POSITIVE LOGITS
     akin
    0.07
     wherein
    0.07
     иное
    0.07
     yielding
    0.06
     cuya
    0.06
     cuja
    0.06
    å°ĨæѤ
    0.05
    æѤçķª
    0.05
    æŶéľĢ
    0.05
    éľĢ
    0.05
    Activations Density 0.003%

    No Known Activations