© 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. 21820
    Prev
    Next
    INDEX
    Explanations

    dialogue markers and transcriptions

    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
    amaha
    -0.06
    ors
    -0.05
     sob
    -0.05
    enan
    -0.05
    طرة
    -0.05
    sob
    -0.05
    eor
    -0.05
    帮åĬ©ä½ł
    -0.05
     vis
    -0.05
    aus
    -0.05
    POSITIVE LOGITS
    éĶĻè¿ĩçļĦ
    0.06
    æ»ļ
    0.06
    溢
    0.06
    çe
    0.06
    ढ
    0.05
    å·®ä¸į
    0.05
    umpt
    0.05
    urit
    0.05
     nisso
    0.05
    olat
    0.05
    Activations Density 0.019%

    No Known Activations