© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20990
    Prev
    Next
    INDEX
    Explanations

    explaining correlations or implications

    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
    eros
    -0.10
     Porno
    -0.10
    端æŃ£
    -0.10
    ATUS
    -0.10
    quil
    -0.09
     понÑĢав
    -0.09
    ingu
    -0.09
    çļĦéĴ±
    -0.09
    _DEPEND
    -0.08
    åľĥ
    -0.08
    POSITIVE LOGITS
    大èĩ´
    0.11
     roughly
    0.09
    æŃ£å¥½
    0.09
    æĦıåij³çĿĢ
    0.09
    3
    0.09
    1
    0.09
    ä¸Ģ个人
    0.09
    6
    0.09
    4
    0.08
    5
    0.08
    Activations Density 0.102%

    No Known Activations