© 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. 51382
    Prev
    Next
    INDEX
    Explanations

    place names after "in"

    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
    水管
    -0.11
    èł¹
    -0.10
     (;;
    -0.08
    _AUD
    -0.08
    çݳ
    -0.08
    æ±īåŃIJ
    -0.08
    .words
    -0.08
    å¸ĸ
    -0.08
    inton
    -0.08
     Fits
    -0.08
    POSITIVE LOGITS
    缮
    0.10
    okes
    0.09
    _eg
    0.09
    å¹ħ
    0.09
     Prospect
    0.08
    æĸĩæĺĮ
    0.08
    äºĨæĪijçļĦ
    0.08
    illac
    0.08
    åĪ°å¤Ħ
    0.08
    对æѤ
    0.08
    Activations Density 0.234%

    No Known Activations