© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20501
    Prev
    Next
    INDEX
    Explanations

    driving, crashes, loss of control

    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
    åĬĽæ±Ĥ
    -0.10
    åIJ®
    -0.09
    è¯Ħ
    -0.09
    åıĪæľī
    -0.09
    æĢĢçĿĢ
    -0.09
     erupted
    -0.08
    鼷æĸ¯
    -0.08
    æģ¶
    -0.08
    usercontent
    -0.08
    æł¹æľ¬å°±ä¸į
    -0.08
    POSITIVE LOGITS
    çºł
    0.10
    éķľå¤´
    0.09
    åĩºå±Ģ
    0.09
    éĵ°
    0.09
    .callbacks
    0.09
    失æݧ
    0.09
    ç¿»
    0.09
     BRAND
    0.08
    æī¯
    0.08
     orbit
    0.08
    Activations Density 0.023%

    No Known Activations