© 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. 19214
    Prev
    Next
    INDEX
    Explanations

    legal action was brought by

    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
    辩æĬ¤
    -0.09
    ÑħоÑĤ
    -0.09
    竦
    -0.09
    rone
    -0.09
    راÙĨ
    -0.09
    affen
    -0.09
     shr
    -0.08
    iment
    -0.08
    PLY
    -0.08
     bè
    -0.08
    POSITIVE LOGITS
    รา
    0.09
    åħ¼åħ·
    0.09
    åĿĿ
    0.09
    å¯ĵ
    0.09
    åĨłåĨĽ
    0.08
    åį¸
    0.08
    olith
    0.08
    licer
    0.08
    åħĪè¡Į
    0.08
    å¸ĪçĶŁ
    0.08
    Activations Density 0.195%

    No Known Activations