© 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. 62485
    Prev
    Next
    INDEX
    Explanations

    proceeds to read or compares

    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
    类产åĵģ
    -0.11
    循
    -0.11
    ä¼´éļı
    -0.10
    çĥŃ线
    -0.10
    å½ĵå±Ģ
    -0.10
    åĵĮ
    -0.10
    åĺ´éĩĮ
    -0.10
    åĺ»åĺ»
    -0.10
    ONY
    -0.09
    便äºİ
    -0.09
    POSITIVE LOGITS
    äºĨä¸Ģç³»åĪĹ
    0.09
     Gi
    0.08
    aller
    0.08
    äºĨä¸Ģ
    0.08
    ä¸Ģç³»åĪĹ
    0.08
    idal
    0.08
    quam
    0.07
    å¼ĢæĪ·
    0.07
    äºĨä¸ĢäºĽ
    0.07
    anka
    0.07
    Activations Density 0.030%

    No Known Activations