© 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. 8051
    Prev
    Next
    INDEX
    Explanations

    cast and crew members

    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
    åŀĽ
    -0.11
    éĺĹ
    -0.09
    èĩªæĿ¥
    -0.09
    媳
    -0.09
    ÑıÑģ
    -0.09
    orent
    -0.09
    ÙĤÙĩ
    -0.09
    åĽ½æľīèµĦ产
    -0.08
    keit
    -0.08
    主ä¹īèĢħ
    -0.08
    POSITIVE LOGITS
    aways
    0.12
    ellation
    0.11
    ings
    0.11
    worthy
    0.11
    ers
    0.10
    room
    0.10
    heets
    0.10
    ively
    0.10
    elli
    0.10
    rooms
    0.09
    Activations Density 0.020%

    No Known Activations