© 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. 22585
    Prev
    Next
    INDEX
    Explanations

    infant distress and crying

    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
    å´´
    -0.10
     dare
    -0.09
     اÙĦØŃÙĬ
    -0.09
    ettes
    -0.08
    OG
    -0.08
    çģµ
    -0.08
    使çĶ¨æĿĥ
    -0.08
    çķª
    -0.08
    ç¼ĵç¼ĵ
    -0.08
    éĺ³åı°
    -0.08
    POSITIVE LOGITS
    å¸®ä½ł
    0.10
    åķ¼
    0.10
    çĥ¦èºģ
    0.10
    åĵŃäºĨ
    0.09
     cry
    0.09
    迷人
    0.09
    åĵŃæ³£
    0.09
    éļĶ
    0.09
     cried
    0.09
    çļĦæĥħ绪
    0.09
    Activations Density 0.035%

    No Known Activations