© 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. 56352
    Prev
    Next
    INDEX
    Explanations

    description patterns based on

    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
    éĵ¤
    -0.11
    çŃīå¤ļç§į
    -0.10
    åħ¶å®ĥ
    -0.10
    åį´æĺ¯
    -0.10
    é¢ĩæľī
    -0.10
    çŃīçī¹çĤ¹
    -0.10
    (other
    -0.10
    reich
    -0.10
    /null
    -0.10
    æĪĸåħ¶ä»ĸ
    -0.10
    POSITIVE LOGITS
    å®ıè§Ĥ
    0.10
    æĺ¯åĽłä¸º
    0.10
     mainly
    0.10
    主è¦ģ
    0.09
    ä¸Ģ个æĺ¯
    0.09
    è¿ĺ好
    0.09
    æŃ£éĿ¢
    0.09
    纵åIJij
    0.09
    人ãģ¨
    0.09
     mostly
    0.09
    Activations Density 0.874%

    No Known Activations