© 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. 18885
    Prev
    Next
    INDEX
    Explanations

    and list items

    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
    ICIP
    -0.08
     **.**
    -0.07
     .**
    -0.07
     fras
    -0.07
    ,__
    -0.07
    )._
    -0.07
    tep
    -0.07
    oor
    -0.07
    :__
    -0.07
    ttp
    -0.06
    POSITIVE LOGITS
     vs
    0.06
     \
    0.05
    es
    0.05
    ag
    0.05
    s
    0.05
     a
    0.05
     from
    0.05
     as
    0.05
     Je
    0.05
    ir
    0.05
    Activations Density 0.045%

    No Known Activations