© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31334
    Prev
    Next
    INDEX
    Explanations

    conveying material fed into machines

    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
    骨
    -0.09
    íĭĢ
    -0.09
    骨干
    -0.08
    èĩªåĪ¶
    -0.08
    åıĺäºĨ
    -0.08
    gis
    -0.08
    BOSE
    -0.08
    prox
    -0.08
     اÙĦÙģت
    -0.08
    ellular
    -0.08
    POSITIVE LOGITS
    éĢģæĸĻ
    0.11
     Pace
    0.11
    anko
    0.09
    æijŃ
    0.09
    otch
    0.09
    æľºæŀĦ
    0.09
    天åłĤ
    0.09
     ожи
    0.08
    移éĢģ
    0.08
    æĭ±
    0.08
    Activations Density 0.465%

    No Known Activations