© 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. 21762
    Prev
    Next
    INDEX
    Explanations

    image reconstruction

    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
    orado
    -0.06
    Ø°
    -0.06
    ucht
    -0.06
    çĥŃ度
    -0.05
    亢
    -0.05
    istou
    -0.05
    Ñĥда
    -0.05
     poros
    -0.05
    ứng
    -0.05
    Angles
    -0.05
    POSITIVE LOGITS
    åŃļ
    0.06
    éĿ©
    0.05
    _like
    0.05
    éĶĻçļĦ
    0.05
    æ¤Ĵ
    0.05
     fray
    0.05
    itty
    0.05
    å®Įåħ¨çļĦ
    0.05
    nüp
    0.05
     detail
    0.05
    Activations Density 0.083%

    No Known Activations