© 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. 17617
    Prev
    Next
    INDEX
    Explanations

    urls matching patterns

    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
    æĪĸå°ij
    -0.07
    æĪĸåĪłéĻ¤
    -0.07
    itol
    -0.07
    enido
    -0.07
    emani
    -0.07
    PED
    -0.06
    æĿŀ
    -0.06
    agra
    -0.06
    ç²¾åįİ
    -0.06
    echos
    -0.06
    POSITIVE LOGITS
    åĮ¹éħį
    0.08
     match
    0.07
     matching
    0.07
     matches
    0.07
     Match
    0.06
    Try
    0.06
     Try
    0.06
     lookup
    0.06
     search
    0.06
    match
    0.06
    Activations Density 0.060%

    No Known Activations