© 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. 33477
    Prev
    Next
    INDEX
    Explanations

    atmospheric chemistry, pollutant accumulation

    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
     Alle
    -0.10
    gne
    -0.09
    Alle
    -0.08
    èŁĭ
    -0.08
    åĨ·æ°´
    -0.08
    lined
    -0.08
    宸
    -0.08
    èŀĪ
    -0.08
    æ¶Įçİ°
    -0.08
    æĪijè¿ĺ
    -0.08
    POSITIVE LOGITS
    éľ¾
    0.13
    é«ĺ空
    0.13
     aeros
    0.12
     Aeros
    0.12
    æªĢ
    0.10
    åĭ¾
    0.10
    为空
    0.10
    éĩĬæĶ¾
    0.09
    çĥŁ
    0.09
    沿éĢĶ
    0.09
    Activations Density 0.108%

    No Known Activations