© 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. 33659
    Prev
    Next
    INDEX
    Explanations

    held out

    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
    oun
    -0.10
    nap
    -0.10
    ะ
    -0.09
    å°±è¿Ļä¹Ī
    -0.09
    ä¸įæĺİ
    -0.09
    éĥ½åĸľæ¬¢
    -0.09
    ç³Ļ
    -0.08
    大æī¹
    -0.08
    è¿Ī
    -0.08
    äºĨä¸Ģæī¹
    -0.08
    POSITIVE LOGITS
    éĿ¥
    0.09
     Signing
    0.09
    sole
    0.09
    岬
    0.08
    aits
    0.08
    åģľè½¦
    0.08
    è¥Ħ
    0.08
    çļĦçģµéŃĤ
    0.08
    èĪĮ
    0.08
    çģ
    0.08
    Activations Density 0.007%

    No Known Activations