© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21508
    Prev
    Next
    INDEX
    Explanations

    extortion attempt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    inger
    -0.09
    骨
    -0.09
    åĬ©
    -0.09
    å°¼æĸ¯
    -0.09
    åŀĤ
    -0.09
    _kwargs
    -0.09
    quette
    -0.08
    åĢľ
    -0.08
    åİĨåı²æĸĩåĮĸ
    -0.08
    约åįł
    -0.08
    POSITIVE LOGITS
    Ñģи
    0.10
    ubs
    0.08
     gar
    0.08
    寡
    0.08
    death
    0.08
    讲解
    0.08
    涵
    0.08
    _EXPECT
    0.08
    ÙĪا
    0.07
     Setter
    0.07
    Activations Density 0.617%

    No Known Activations