© 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. 17483
    Prev
    Next
    INDEX
    Explanations

    attractions

    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
    -0.08
     takeaway
    -0.06
    çľĭæĿ¥
    -0.06
    aning
    -0.05
     element
    -0.05
     hekt
    -0.05
     chance
    -0.05
    å¾ħ
    -0.05
    OUND
    -0.05
    aley
    -0.05
    POSITIVE LOGITS
    ghi
    0.07
    igno
    0.06
    sWith
    0.06
    gee
    0.06
    adop
    0.06
    ,private
    0.06
     ets
    0.06
    ymes
    0.06
    orks
    0.05
     privately
    0.05
    Activations Density 0.018%

    No Known Activations