© 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. 21698
    Prev
    Next
    INDEX
    Explanations

    method="post"

    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
    é«ĺå¼Ģ
    -0.06
    bra
    -0.06
    aqu
    -0.06
    âĢ¦Â»
    -0.06
    rette
    -0.06
    (fabs
    -0.06
    egot
    -0.06
    hern
    -0.05
    ilmington
    -0.05
    NDER
    -0.05
    POSITIVE LOGITS
    fu
    0.07
    ils
    0.06
    elé
    0.05
     Rua
    0.05
    iony
    0.05
    ifs
    0.05
    crement
    0.05
    zny
    0.05
    еÑģÑĤ
    0.05
    course
    0.05
    Activations Density 0.005%

    No Known Activations