© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19907
    Prev
    Next
    INDEX
    Explanations

    wide receiver or tight end

    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
    forma
    -0.09
    cased
    -0.09
     danske
    -0.09
    åĽŀäºĭ
    -0.09
    ä¸Ńä»ĭ
    -0.08
     Leather
    -0.08
     rem
    -0.08
     меÑħ
    -0.08
    navbarSupportedContent
    -0.08
    çĪ·
    -0.08
    POSITIVE LOGITS
     Freeman
    0.09
    -scrollbar
    0.09
    oir
    0.09
    elin
    0.09
    ä¼ĹæīĢ
    0.08
    .sun
    0.08
    çĶŁçī©åѦ
    0.08
    åijĺ
    0.08
    arov
    0.08
    åºĵ
    0.08
    Activations Density 0.007%

    No Known Activations