© 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. 59197
    Prev
    Next
    INDEX
    Explanations

    burning, flaming, ignite, flames, fire

    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
    æı½
    -0.08
    å®īåħ¨ä¿Ŀéļľ
    -0.08
    æ²±
    -0.08
    å¹ħ
    -0.08
    ConfigurationException
    -0.08
     Orleans
    -0.08
    lus
    -0.08
    urer
    -0.08
    西è£ħ
    -0.08
    _ENSURE
    -0.07
    POSITIVE LOGITS
    çģ¼
    0.16
    çĩĥçĥ§
    0.15
    çĩĴ
    0.14
    çĤī
    0.14
    çģ¶
    0.14
    ðŁĶ¥
    0.14
     cháy
    0.14
    çĥĪ
    0.13
    çĦļçĥ§
    0.13
    -hot
    0.13
    Activations Density 0.104%

    No Known Activations