© 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. 20709
    Prev
    Next
    INDEX
    Explanations

    imported words, phrases, or parts

    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
    ufe
    -0.07
     bénéfic
    -0.06
    ekl
    -0.06
    éľĢè¦ģä¸Ģ个
    -0.06
    åĿļ
    -0.06
    emoc
    -0.06
     nationwide
    -0.06
    ило
    -0.06
     filtra
    -0.06
    imson
    -0.06
    POSITIVE LOGITS
    orts
    0.06
    çĿ£
    0.06
    oret
    0.06
    λÏħ
    0.05
    vid
    0.05
    éļı
    0.05
     ‘
    0.04
    itr
    0.04
    ood
    0.04
    äre
    0.04
    Activations Density 0.022%

    No Known Activations