© 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. 4543
    Prev
    Next
    INDEX
    Explanations

    Hawaii, Maui, Guam, islands, names

    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
    abb
    -0.10
    çĤ¹ç¼Ģ
    -0.09
    åľ¨æĦı
    -0.09
     derail
    -0.09
    REL
    -0.09
    å¤ĸå½¢
    -0.09
    éĤ³
    -0.09
    çĭ°
    -0.09
    ango
    -0.08
    çĵ£
    -0.08
    POSITIVE LOGITS
    ç¾¤å²Ľ
    0.10
     Hawaii
    0.09
    peater
    0.09
     Alexand
    0.09
    åĽ°
    0.09
    访
    0.08
    æªĢ
    0.08
     Guam
    0.08
    磨
    0.08
    ç¼Ķ
    0.08
    Activations Density 0.014%

    No Known Activations