© 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. 37968
    Prev
    Next
    INDEX
    Explanations

    further more

    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
    éĢļä¿Ĺ
    -0.09
    æĺ¶
    -0.09
    pen
    -0.09
    ä¸ŃåĽ½æ¢¦
    -0.09
    èĺĸ
    -0.08
    ptr
    -0.08
     Charity
    -0.08
    æĸŃè£Ĥ
    -0.08
    çĺ¦èº«
    -0.08
    åĪ½
    -0.08
    POSITIVE LOGITS
    éĻį
    0.10
    ä¸Ģæĸ¹
    0.10
     Stark
    0.09
    HD
    0.09
    轶
    0.08
    IDER
    0.08
     HD
    0.08
    åĬ£
    0.08
    æĸ°ä¸ī
    0.08
    éĺ´å½±
    0.08
    Activations Density 3.997%

    No Known Activations