© 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. 17371
    Prev
    Next
    INDEX
    Explanations

    place names or types

    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
    teau
    -0.07
    warts
    -0.06
    appareil
    -0.06
    æĸ¹æ¡Ī
    -0.06
    éĹľæĩ·
    -0.06
    ighton
    -0.06
    åħ³æĢĢ
    -0.06
    _path
    -0.06
    cales
    -0.05
     pertinente
    -0.05
    POSITIVE LOGITS
    ibu
    0.05
    лож
    0.05
    äºĨä¸ĢèĪ¬
    0.05
    æĭĽ
    0.05
     trans
    0.05
    oke
    0.05
    æĹ
    0.05
    ici
    0.05
    nk
    0.05
     transpose
    0.05
    Activations Density 0.002%

    No Known Activations