© 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. 19195
    Prev
    Next
    INDEX
    Explanations

    not missed, not caught, not undergoing

    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
    —not
    -0.05
     denen
    -0.05
    åºĶ对
    -0.05
    å¿
    -0.05
    ocket
    -0.05
    sy
    -0.05
     nor
    -0.04
    ceptors
    -0.04
    cers
    -0.04
    Âł
    -0.04
    POSITIVE LOGITS
    ÙĪØ«
    0.07
    ghi
    0.07
     proposons
    0.06
    onna
    0.06
    innt
    0.06
    zon
    0.06
    orn
    0.06
    æļĤè¡Į
    0.06
     saja
    0.06
    joint
    0.06
    Activations Density 0.024%

    No Known Activations