© 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. 1066
    Prev
    Next
    INDEX
    Explanations

    medical emergency presentation

    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
    çĽijçĿ£
    -0.10
     hindsight
    -0.10
    éĶħçĤī
    -0.10
    feit
    -0.10
    åıij声
    -0.09
    IRTUAL
    -0.09
    èĩªåľ¨
    -0.09
     ден
    -0.09
    ipers
    -0.09
    çĿ£
    -0.09
    POSITIVE LOGITS
    æĬ¢æķij
    0.13
    æĢ¥æķij
    0.13
    绿èī²éĢļéģĵ
    0.12
    æķijåĬ©
    0.11
    æķijæĬ¤
    0.10
    èħĭ
    0.10
    æķijæ²»
    0.10
    æķijåij½
    0.10
    æķijæı´
    0.09
     Bols
    0.09
    Activations Density 0.265%

    No Known Activations