© 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. 17831
    Prev
    Next
    INDEX
    Explanations

    Almighty Earl Adonis

    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
    IsValid
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    leans
    -0.06
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.06
    è¿Ļç§įæĦŁè§ī
    -0.06
    idé
    -0.06
    semble
    -0.06
    prd
    -0.06
    è¿ĻèĤ¡
    -0.06
    :len
    -0.06
    POSITIVE LOGITS
    cu
    0.05
    说æĺİ
    0.05
    owo
    0.05
    city
    0.05
    ouble
    0.05
    nbsp
    0.05
    trs
    0.05
    ijas
    0.05
    커
    0.05
    c
    0.05
    Activations Density 0.001%

    No Known Activations