© 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. 17485
    Prev
    Next
    INDEX
    Explanations

    import (...)

    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
    ornamento
    -0.06
    entar
    -0.06
    ifle
    -0.06
    otts
    -0.06
    ]->
    -0.06
    åħ¶çĥ¦
    -0.06
    产ä¸ļçļĦ
    -0.06
    ible
    -0.06
    ÑĬ
    -0.05
    ä¸ĭæīĭ
    -0.05
    POSITIVE LOGITS
    yka
    0.05
     raccontato
    0.05
    inst
    0.05
     tamp
    0.05
    vam
    0.05
     sign
    0.05
    æª
    0.05
     del
    0.05
    ä¸Ĭ大
    0.05
    &E
    0.05
    Activations Density 0.006%

    No Known Activations