© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19625
    Prev
    Next
    INDEX
    Explanations

    ordinal placings

    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
     صÙĪرت
    -0.06
     off
    -0.06
     usu
    -0.06
    usty
    -0.06
    ish
    -0.06
    ized
    -0.05
    .aw
    -0.05
    orea
    -0.05
    ä¼Łå¤§
    -0.05
    çī¡
    -0.05
    POSITIVE LOGITS
    ÓĻн
    0.06
     rival
    0.06
    afen
    0.06
    IGH
    0.06
    vä
    0.05
    vie
    0.05
    angstrom
    0.05
    cich
    0.05
    igh
    0.05
     méda
    0.05
    Activations Density 0.002%

    No Known Activations