© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29387
    Prev
    Next
    INDEX
    Explanations

    aside, barring, irrespective, regardless, independently

    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
    Negative Logits
    brew
    -0.10
    åħ¨æĸ¹ä½į
    -0.09
    ower
    -0.09
    æºĥ
    -0.08
    æĴij
    -0.08
    åĥµ
    -0.08
    å§ĭç»ĪåĿļæĮģ
    -0.08
    alin
    -0.08
    @s
    -0.08
    è¿°èģĮ
    -0.08
    POSITIVE LOGITS
    ä¸į说
    0.15
     aside
    0.13
    èĥ½åIJ¦
    0.10
    以å¤ĸ
    0.10
    ä¹ĭå¤ĸ
    0.10
    å¦Ĥä½ķåİ»
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    å¦Ĥä½ķçľĭå¾ħ
    0.09
    èĥ½ä¸įèĥ½
    0.09
    ä¸į论
    0.09
    Activations Density 0.068%

    No Known Activations