© 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. 51631
    Prev
    Next
    INDEX
    Explanations

    public health problems and emergencies

    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
    åĽ¢éķ¿
    -0.09
    äºİæѤ
    -0.09
    .ur
    -0.09
    æµij
    -0.09
    QUEST
    -0.08
    oret
    -0.08
    éĢīæĭĶ
    -0.08
    çĹħæĥħ
    -0.08
     Rip
    -0.08
    fas
    -0.08
    POSITIVE LOGITS
    å·¥ä½ľèĢħ
    0.09
    веÑī
    0.09
     circ
    0.08
    street
    0.08
    (all
    0.08
    raud
    0.08
    IL
    0.08
    ione
    0.08
    retty
    0.08
    å±ıéļľ
    0.08
    Activations Density 0.024%

    No Known Activations