© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20173
    Prev
    Next
    INDEX
    Explanations

    Understanding Research

    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
    av
    -0.06
    ny
    -0.06
    avid
    -0.06
     spannend
    -0.06
    å¤ĩ
    -0.05
    اس
    -0.05
    帮åĬ©å¤§å®¶
    -0.05
    ÑĢÑİ
    -0.05
    ÑĥÑĩ
    -0.05
    ice
    -0.05
    POSITIVE LOGITS
    leges
    0.06
    ingles
    0.05
    že
    0.05
    ciales
    0.05
    qü
    0.05
    常æĢģ
    0.05
    éĿ
    0.05
    zol
    0.05
    åIJŀ
    0.05
    бов
    0.05
    Activations Density 0.041%

    No Known Activations