© 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. 18861
    Prev
    Next
    INDEX
    Explanations

    grist mill located near

    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
    åħ¥å¸Ĥ
    -0.10
    éĢŁ
    -0.09
    çĶ¨åľ°
    -0.09
    åĽŃæŀĹ
    -0.09
    è´µ
    -0.09
    äºĶä¸Ģ
    -0.09
    å¸Ĥä¸Ńå¿ĥ
    -0.09
    æľ¬å¸Ĥ
    -0.08
    ks
    -0.08
    åį¿
    -0.08
    POSITIVE LOGITS
    åĪ¶
    0.09
    溪
    0.09
    è¾ĥéķ¿
    0.09
     Homes
    0.09
    ariat
    0.09
    驼
    0.08
    èį¨
    0.08
     plung
    0.08
    ÑĮÑİ
    0.08
    éĥ¿
    0.08
    Activations Density 0.132%

    No Known Activations