© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21314
    Prev
    Next
    INDEX
    Explanations

    genotypes and alleles

    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
    å¾ĹæĦı
    -0.10
    çĶ¸
    -0.10
    çŀİ
    -0.09
    itzer
    -0.09
    ä»ĸå¦Ī
    -0.09
    å·¡åĽŀ
    -0.09
    xfb
    -0.08
    éľģ
    -0.08
    çĸ³
    -0.08
    å¾ģæĶ¶
    -0.08
    POSITIVE LOGITS
    çĥĺ
    0.09
    å®Į好
    0.09
    ä¸įè§ģ
    0.09
     adv
    0.08
    衬
    0.08
    laus
    0.08
    wers
    0.08
    æĺ¾éľ²
    0.08
     presence
    0.08
     recess
    0.08
    Activations Density 0.190%

    No Known Activations