© 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. 17302
    Prev
    Next
    INDEX
    Explanations

    personal narrative, anecdotes, and recollections

    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
     handler
    -0.05
    handler
    -0.05
    sid
    -0.05
    ""
    -0.05
     Invalidate
    -0.05
    以åħ¶
    -0.05
    å¾Ģ
    -0.05
    好åķĬ
    -0.05
    è°ģ
    -0.05
    æ±Ĺ
    -0.05
    POSITIVE LOGITS
    ä¸įèĪį
    0.08
    odor
    0.07
    eti
    0.06
    igue
    0.06
    äºĭå®ŀä¸Ĭ
    0.06
    orme
    0.05
    uxe
    0.05
    ibel
    0.05
    rut
    0.05
    èľĤçªĿ
    0.05
    Activations Density 0.020%

    No Known Activations