© 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. 53025
    Prev
    Next
    INDEX
    Explanations

    way to do something

    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
    åĩĿ
    -0.09
    åħ¨æĹ¥
    -0.09
     ÑģобÑģÑĤвенно
    -0.08
    éĨį
    -0.08
    jian
    -0.08
    驼
    -0.08
    ãģ£ãģįãĤĬ
    -0.08
     ëĶ°
    -0.08
    便
    -0.08
    åģļçļĦäºĭ
    -0.08
    POSITIVE LOGITS
    æĥ³åĬŀæ³ķ
    0.17
    åĬŀæ³ķ
    0.14
    æĢ»æľī
    0.14
    åħĭæľį
    0.13
    à¹Ģสมà¸Ń
    0.13
    è°ĥæķ´
    0.12
     somehow
    0.12
    èĥ½æī¾åĪ°
    0.12
    éĢĤåºĶ
    0.12
    æĢ»ä¼ļ
    0.12
    Activations Density 0.076%

    No Known Activations