© 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. 20179
    Prev
    Next
    INDEX
    Explanations

    code syntax and variable assignment

    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
    "
    -0.05
    act
    -0.05
    **
    -0.05
    ↵
    -0.05
    *
    -0.05
    (
    -0.05
    ister
    -0.05
    ami
    -0.05
    R
    -0.05
    h
    -0.04
    POSITIVE LOGITS
    имÑĥ
    0.08
    новÑĥ
    0.08
    latego
    0.08
    à¸IJ
    0.07
    vodu
    0.07
    ždy
    0.07
    киÑģло
    0.07
     bezo
    0.07
    eniu
    0.07
    æľ¬ç¤¾
    0.07
    Activations Density 0.014%

    No Known Activations