© 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. 21409
    Prev
    Next
    INDEX
    Explanations

    link above

    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
    ity
    -0.09
    á»ĩt
    -0.09
    çĸ¤
    -0.09
     Vo
    -0.09
    åıī
    -0.08
    paque
    -0.08
     Compatibility
    -0.08
    à¹ģà¸Ī
    -0.08
    çħ§
    -0.08
    æī¿æİ¥
    -0.08
    POSITIVE LOGITS
     advertisement
    0.10
    è§ģåĪ°
    0.09
     Dich
    0.09
    pees
    0.08
     advert
    0.08
    为人
    0.08
    /library
    0.08
     advertisements
    0.08
    åī²
    0.08
    ogen
    0.08
    Activations Density 0.040%

    No Known Activations