© 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. 7879
    Prev
    Next
    INDEX
    Explanations

    all time

    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
    -ish
    -0.10
     dÃłng
    -0.09
     Dob
    -0.09
    丼
    -0.09
    onth
    -0.09
    çĭ·
    -0.09
    çļĦä¸ĢåĪĩ
    -0.09
    çĥĽ
    -0.09
    unas
    -0.09
    ä¸İåIJ¦
    -0.09
    POSITIVE LOGITS
    åĨ¶
    0.09
     irony
    0.09
    iron
    0.09
    eed
    0.08
    possible
    0.08
    两侧
    0.08
     possible
    0.08
     Possible
    0.08
     возмож
    0.07
    åİŁåĽłæĺ¯
    0.07
    Activations Density 0.008%

    No Known Activations