© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19916
    Prev
    Next
    INDEX
    Explanations

    components connected by or alongside others

    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
     transient
    -0.06
    ä¸įåIJĮæŶ
    -0.06
    avy
    -0.06
    atter
    -0.06
    thon
    -0.05
     different
    -0.05
    ä¸įåIJĮ
    -0.05
    ambul
    -0.05
     instantiated
    -0.05
     detal
    -0.05
    POSITIVE LOGITS
     alongside
    0.07
    éħį以
    0.06
     affian
    0.06
     seguido
    0.06
    çĦ¶åIJİåĨį
    0.06
     followed
    0.06
    éħįä¸Ĭ
    0.06
    à®Łà®©à¯į
    0.06
     diikuti
    0.06
    à¸Ļำ
    0.06
    Activations Density 0.269%

    No Known Activations