© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19558
    Prev
    Next
    INDEX
    Explanations

    selling goods or services

    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
    onet
    -0.07
    Sales
    -0.07
    á»ĩ
    -0.07
    iskus
    -0.07
    ahasa
    -0.07
    ulist
    -0.07
    lest
    -0.07
    Ñĩего
    -0.06
     tact
    -0.06
    idades
    -0.06
    POSITIVE LOGITS
    ings
    0.06
    лаг
    0.05
     C
    0.05
    fra
    0.05
     Lane
    0.05
    ingly
    0.05
     mac
    0.05
    rie
    0.05
    å¦Ĥåľ¨
    0.05
    oir
    0.05
    Activations Density 0.012%

    No Known Activations