© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35988
    Prev
    Next
    INDEX
    Explanations

    gene therapy and diseases

    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
    ewire
    -0.10
    çĹ£
    -0.10
    omite
    -0.09
    è·Ĺ
    -0.09
    ewise
    -0.09
    бе
    -0.09
    ðŁĺ·
    -0.09
     McCain
    -0.08
    oldt
    -0.08
    å½ķ
    -0.08
    POSITIVE LOGITS
    客æľį
    0.10
    ä¸Ĭä¸ĭ游
    0.09
    çŃī级
    0.09
     bat
    0.09
    å¯ĴåĨ¬
    0.08
    Ñīе
    0.08
    xo
    0.08
    åħĭåĪ¶
    0.08
    æµ·åºķ
    0.08
    nio
    0.08
    Activations Density 0.317%

    No Known Activations