© 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. 18714
    Prev
    Next
    INDEX
    Explanations

    mixing or together

    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
    .fore
    -0.10
    åıĺå¼Ĥ
    -0.10
    äºĨä¸Ģåı¥
    -0.10
    ä¸įæĩĪ
    -0.09
    ä¸į容
    -0.09
    çĹħæ¯ĴæĦŁæŁĵ
    -0.09
    otron
    -0.09
    stakes
    -0.09
    æī¶
    -0.09
    æݨåĩº
    -0.09
    POSITIVE LOGITS
    æ··åIJĪ
    0.12
     mixing
    0.12
    æ··
    0.11
    Seg
    0.11
     mixed
    0.10
     MIX
    0.10
     Seg
    0.10
    åħ¬åħ±èµĦæºIJ
    0.10
    _MIX
    0.10
     Mixing
    0.10
    Activations Density 0.052%

    No Known Activations