© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57457
    Prev
    Next
    INDEX
    Explanations

    bullying, bully, stalking

    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
    æķĻè®Ń
    -0.09
    ä¹Ķ丹
    -0.09
    FileManager
    -0.08
    ooth
    -0.08
    æĴŀ
    -0.08
    被çĽĹ
    -0.08
    кле
    -0.08
    çݩ家们
    -0.08
    åIJĮå¿Ĺ们
    -0.08
    .addObject
    -0.08
    POSITIVE LOGITS
    olk
    0.10
    æĭĬ
    0.10
    sters
    0.09
    aire
    0.09
     ÃŃch
    0.09
     dáng
    0.09
    bench
    0.09
    -death
    0.09
    æĮĩæķ°
    0.09
    aise
    0.09
    Activations Density 0.004%

    No Known Activations