© 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. 20813
    Prev
    Next
    INDEX
    Explanations

    project elements

    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
     magnitude
    -0.06
    .t
    -0.06
    akens
    -0.06
    vice
    -0.06
    ...\
    -0.05
    chet
    -0.05
    tif
    -0.05
    cor
    -0.05
    arto
    -0.05
     halfway
    -0.05
    POSITIVE LOGITS
     âĦĸ
    0.06
     III
    0.06
    第
    0.05
     II
    0.05
    æŁIJ
    0.05
     pesta
    0.05
    æŀľçľŁ
    0.05
     VII
    0.05
    çĶ²
    0.05
    illy
    0.05
    Activations Density 0.158%

    No Known Activations