© 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. 21142
    Prev
    Next
    INDEX
    Explanations

    multi- with compound words, hyphenated

    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
    ами
    -0.07
    eor
    -0.07
    ptions
    -0.07
    ап
    -0.06
    idges
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    ohl
    -0.06
    е
    -0.06
    ezas
    -0.06
    以轻
    -0.06
    POSITIVE LOGITS
    way
    0.07
    stood
    0.07
    shire
    0.07
    aly
    0.07
    ed
    0.07
    mann
    0.06
    o
    0.06
    å±ĤçļĦ
    0.06
    веÑģÑĤ
    0.06
    plic
    0.06
    Activations Density 0.039%

    No Known Activations