© 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. 62009
    Prev
    Next
    INDEX
    Explanations

    form, produce, yield, establish

    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
    åīįè¿°
    -0.09
    arrass
    -0.09
    æ£Ģ
    -0.09
    abin
    -0.09
    åĩºåľº
    -0.08
    åĩĨå¤ĩå·¥ä½ľ
    -0.08
     Hague
    -0.08
    ncia
    -0.08
    äºĨåĩºæĿ¥
    -0.08
    atten
    -0.08
    POSITIVE LOGITS
    å½¢æĪIJ
    0.17
    å½¢æĪIJäºĨ
    0.13
    产çĶŁ
    0.11
    è¡įçĶŁ
    0.11
    éĢłæĪIJ
    0.10
    ç»Ļåĩº
    0.10
    çķĻä¸ĭ
    0.10
    å¾Ĺåĩº
    0.10
    å½¢æĪIJçļĦ
    0.09
    æ¢Ń
    0.09
    Activations Density 0.054%

    No Known Activations