© 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. 19073
    Prev
    Next
    INDEX
    Explanations

    .It

    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
    /{}/
    -0.07
    好ä¸į
    -0.07
     Altro
    -0.07
    isky
    -0.07
    復åı¤
    -0.07
    swer
    -0.06
    ÑģÑĤеÑģÑĤвенно
    -0.06
    ä¸įæħİ
    -0.06
    atico
    -0.06
     quartos
    -0.06
    POSITIVE LOGITS
    d
    0.06
     ever
    0.05
     "
    0.05
     Spiegel
    0.05
    c
    0.05
     sing
    0.05
    guard
    0.05
     “
    0.05
    k
    0.05
     sp
    0.05
    Activations Density 0.002%

    No Known Activations