© 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. 20032
    Prev
    Next
    INDEX
    Explanations

    negatives and oppositions

    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
    uds
    -0.05
    ops
    -0.05
    åŃ£åIJİ
    -0.05
     Feinstein
    -0.05
    责任ç¼ĸè¾ij
    -0.05
    .UtcNow
    -0.05
    à¸Ńุ
    -0.05
    èį¯çī©æ²»çĸĹ
    -0.05
    lier
    -0.05
    egers
    -0.05
    POSITIVE LOGITS
    éĤ£é¢Ĺ
    0.06
    fort
    0.06
    èİĺ
    0.06
    agerie
    0.05
    åīįäºĶ
    0.05
    zenia
    0.05
    KOM
    0.05
    ëŀĺ
    0.05
    astas
    0.05
    olk
    0.05
    Activations Density 0.001%

    No Known Activations