© 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. 57811
    Prev
    Next
    INDEX
    Explanations

    Anthropogenic or anth- prefixes

    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
    ingly
    -0.12
    -0.09
    åĩºå¤Ħ
    -0.09
    stä
    -0.09
    icas
    -0.08
    urat
    -0.08
    etz
    -0.08
    å°ıä¼Ļ
    -0.08
    åħħ足çļĦ
    -0.08
    etable
    -0.08
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.11
    äºĨ个
    0.10
    äºĨä¸įå°ij
    0.10
    æ¶ķ
    0.09
    atcher
    0.09
    auge
    0.09
    äºĨèĩªå·±çļĦ
    0.09
    æ§ģ
    0.09
    ãģ£ãģįãĤĬ
    0.09
    elves
    0.09
    Activations Density 0.019%

    No Known Activations