© 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. 31630
    Prev
    Next
    INDEX
    Explanations

    accident report

    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
    榻
    -0.12
    å¼Ľ
    -0.11
    æĭ§
    -0.10
    åķĨä¸ļåĮĸ
    -0.09
     Angus
    -0.09
    å¢ģ
    -0.09
     ÑģÑĤанд
    -0.09
    doch
    -0.08
     tuned
    -0.08
    elay
    -0.08
    POSITIVE LOGITS
    交éĢļå®īåħ¨
    0.12
    交éĢļäºĭæķħ
    0.11
    äºĭæķħ
    0.10
    åı¯æĢľ
    0.10
    _traffic
    0.09
     Archer
    0.09
    nett
    0.09
    acci
    0.09
     accident
    0.09
    éĻį临
    0.09
    Activations Density 0.110%

    No Known Activations