© 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. 39479
    Prev
    Next
    INDEX
    Explanations

    safety incidents and accidents

    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
    èµĭäºĪ
    -0.08
    ç¼¥
    -0.08
    ancers
    -0.08
    èĬĤ
    -0.08
    (UINT
    -0.08
    èľĤ
    -0.08
    æ¢Ń
    -0.08
    äººæł¼
    -0.08
    éģĩè§ģ
    -0.08
     libros
    -0.08
    POSITIVE LOGITS
    äºĭæķħ
    0.18
    å®īåħ¨ç®¡çIJĨ
    0.11
    incident
    0.11
    æķĻè®Ń
    0.11
     incident
    0.11
     accident
    0.11
    åIJ¸åıĸ
    0.11
    äºĭæķħåıijçĶŁ
    0.11
     Incident
    0.11
    LEC
    0.11
    Activations Density 0.090%

    No Known Activations