© 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. 7083
    Prev
    Next
    INDEX
    Explanations

    contrast or newness

    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
     similarities
    -0.12
     similarity
    -0.10
    æĹłåħ³
    -0.10
    çĽ¸ä¼¼
    -0.10
    pulse
    -0.09
    毫æĹłçĸij
    -0.09
    å·²ç»ıæľī
    -0.09
    没éĹ®é¢ĺ
    -0.09
     Similar
    -0.09
     Already
    -0.09
    POSITIVE LOGITS
    Fresh
    0.12
     novel
    0.11
    æľīå¿ħè¦ģ
    0.11
    nov
    0.11
     novelty
    0.11
    æĸ°é²ľ
    0.10
     Fresh
    0.10
    èµĽ
    0.10
    é²ľ
    0.10
    éĻĮçĶŁ
    0.10
    Activations Density 0.123%

    No Known Activations