© 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. 20916
    Prev
    Next
    INDEX
    Explanations

    decorators and framework annotations

    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
    an
    -0.06
    ed
    -0.06
    able
    -0.06
    hea
    -0.05
    board
    -0.05
    acz
    -0.05
    ing
    -0.05
    ĥĿ
    -0.05
    åIJijåĨħ
    -0.05
    aza
    -0.05
    POSITIVE LOGITS
    lemn
    0.06
    ÙĬتÙĬÙĨ
    0.06
    ulin
    0.06
    arest
    0.06
     latter
    0.05
    ujo
    0.05
    sembly
    0.05
    åĩłå£°
    0.05
    TRY
    0.05
     wont
    0.05
    Activations Density 0.001%

    No Known Activations