© 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. 30508
    Prev
    Next
    INDEX
    Explanations

    fun, entertaining, drama, tense

    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
    ãģĻãģĶ
    -0.09
    温æŁĶ
    -0.09
    çļĦçľ¼åħī
    -0.09
    åij½åIJį为
    -0.09
    èĥĻ
    -0.09
    Ùģات
    -0.08
    ç¥ŀå¥ĩ
    -0.08
    ä¸įæ¸ħ
    -0.08
    ä¸įæĪIJ
    -0.08
    å¾ĪæŃ£å¸¸
    -0.08
    POSITIVE LOGITS
    大åݦ
    0.09
    ä¹ĭæĪĺ
    0.09
    éĺ²å¾¡
    0.09
    ientes
    0.08
    hof
    0.08
     CharSequence
    0.08
    ç«ĭä½ĵ
    0.08
    çĪ½
    0.08
     Proud
    0.08
    趾
    0.08
    Activations Density 0.063%

    No Known Activations