© 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. 39964
    Prev
    Next
    INDEX
    Explanations

    enough

    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
     nin
    -0.09
    éĹ®éĹ®
    -0.09
    FAQ
    -0.09
    碣
    -0.09
    åĬ©åѦ
    -0.09
    çĽĺæ´»
    -0.08
     Carp
    -0.08
     Cheers
    -0.08
     Ñĥме
    -0.08
     Chuck
    -0.08
    POSITIVE LOGITS
    ä¸įèĥ½åĨį
    0.13
     Enough
    0.11
    å¤Ł
    0.11
    å¤ł
    0.11
    Enough
    0.11
    ä¸įåĨį
    0.10
    åĨįä¹Ł
    0.10
    à¸Ĺà¸Ļ
    0.10
     enough
    0.10
    cki
    0.10
    Activations Density 0.031%

    No Known Activations