© 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. 19691
    Prev
    Next
    INDEX
    Explanations

    expect to

    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
    è¾°
    -0.10
     Schwartz
    -0.09
    ç½ķè§ģ
    -0.09
    å®ŀæĥł
    -0.08
    çIJĩ
    -0.08
     ea
    -0.08
     лиÑĪ
    -0.08
    åī¯
    -0.08
    失æݧ
    -0.08
    åĮºåĪĨ
    -0.08
    POSITIVE LOGITS
    æĮĩæľĽ
    0.16
    ä¼ģåĽ¾
    0.15
    è¯ķåĽ¾
    0.14
    æľŁæľĽ
    0.13
    奢
    0.13
    å¦Ħ
    0.13
    éĹ®æĪij
    0.13
    åĩŃä»Ģä¹Ī
    0.12
    æĥ³è¦ģ
    0.12
    å¸ĮæľĽèĥ½å¤Ł
    0.12
    Activations Density 0.083%

    No Known Activations