© 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. 17545
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    àºĹີ
    -0.07
    resto
    -0.06
    acz
    -0.06
    ertura
    -0.06
    mux
    -0.06
    union
    -0.06
    edin
    -0.06
    althy
    -0.06
    owel
    -0.06
    érit
    -0.06
    POSITIVE LOGITS
    0.07
    ä¸įæĭĶ
    0.05
    .
    0.05
    inat
    0.05
    isp
    0.05
     ph
    0.05
    ,
    0.05
     ram
    0.04
    igth
    0.04
    æĽ´åĬłæ³¨éĩį
    0.04
    Activations Density 0.000%

    No Known Activations