© 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. 50431
    Prev
    Next
    INDEX
    Explanations

    edit, change, add, uncomment, comment

    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
    aji
    -0.10
    çIJ
    -0.09
    èĬĿ麻
    -0.09
    subs
    -0.09
    ä¸į便
    -0.08
    outs
    -0.08
     Freed
    -0.08
    çĬ¶åħĥ
    -0.08
    DET
    -0.08
    èµģ
    -0.08
    POSITIVE LOGITS
    éĢĤå½ĵ
    0.11
    ä¸Ģå¤Ħ
    0.11
    æľīåħ³éĥ¨éŨ
    0.10
    éĢĤå½ĵçļĦ
    0.10
    åĬłå¤§å¯¹
    0.09
    缸åħ³éĥ¨éŨ
    0.09
    大åĬĽ
    0.09
    å¢ŀåĬłåĢ¼
    0.09
    ä¿®æĶ¹
    0.09
    å¦Ĥä¸ĭ
    0.09
    Activations Density 0.508%

    No Known Activations