© 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. 20285
    Prev
    Next
    INDEX
    Explanations

    abstract or abstract

    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
    ÑĢек
    -0.06
    cier
    -0.06
    agni
    -0.06
    cking
    -0.05
    xF
    -0.05
    acun
    -0.05
    endah
    -0.05
    æĪŁ
    -0.05
    æĥķ
    -0.05
    kson
    -0.05
    POSITIVE LOGITS
    SPA
    0.06
     allotted
    0.05
    at
    0.05
    rogate
    0.05
    à¸IJาà¸Ļ
    0.05
    rit
    0.05
    æĥ³è¦ģçļĦ
    0.05
    artial
    0.05
    èIJ¥éĢłä¸Ģ个
    0.05
    驳
    0.05
    Activations Density 0.015%

    No Known Activations