© 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. 20548
    Prev
    Next
    INDEX
    Explanations

    application instances

    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
    rawd
    -0.07
    riel
    -0.07
    inite
    -0.07
    tempts
    -0.06
    nip
    -0.06
    姥
    -0.06
     competen
    -0.06
    raud
    -0.06
     Elem
    -0.06
    grap
    -0.06
    POSITIVE LOGITS
     output
    0.05
     stream
    0.05
    arch
    0.05
    幸ç¦ıçļĦ
    0.05
     cris
    0.05
    output
    0.05
    è¿ĺ好
    0.05
    hic
    0.04
    0.04
    Âł
    0.04
    Activations Density 0.047%

    No Known Activations