© 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. 17227
    Prev
    Next
    INDEX
    Explanations

    divided by

    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
     Äijâu
    -0.06
     siden
    -0.06
    ãģĵãģ¡ãĤīãĤĤ
    -0.05
     Kampung
    -0.05
     Capit
    -0.05
    variably
    -0.05
    åĩºä¹İ
    -0.05
    pect
    -0.05
    ello
    -0.05
    quiry
    -0.05
    POSITIVE LOGITS
    isations
    0.06
    alise
    0.06
    izations
    0.06
    inch
    0.06
    subclass
    0.06
    åĮĸçļĦ
    0.06
    使
    0.05
    ments
    0.05
     sot
    0.05
    iams
    0.05
    Activations Density 0.008%

    No Known Activations