© 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. 51136
    Prev
    Next
    INDEX
    Explanations

    mass suicide, surveillance, casualty, murderer, shooting

    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
    /cms
    -0.10
     tricks
    -0.10
    _fault
    -0.09
    èį¯å¸Ī
    -0.09
    æijĩ头
    -0.09
     ÐĶм
    -0.09
    åĢ¼çıŃ
    -0.09
    lds
    -0.09
    umed
    -0.08
    å¥Ī
    -0.08
    POSITIVE LOGITS
     mass
    0.11
    mass
    0.10
    .mass
    0.10
    stre
    0.09
     маÑģÑģ
    0.09
    å±ł
    0.09
    主ä¹īèĢħ
    0.09
    ä»İ严
    0.09
    åİ¥
    0.09
    æİĪ
    0.09
    Activations Density 0.023%

    No Known Activations