© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29550
    Prev
    Next
    INDEX
    Explanations

    earth related phenomena

    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
    Negative Logits
    ERA
    -0.09
    ohon
    -0.09
    åĽ½å®ī
    -0.09
    亵
    -0.09
    éªģ
    -0.09
    .VK
    -0.09
    è¡Ļ
    -0.09
    اتÙĩا
    -0.09
    atha
    -0.09
    çŃīå½¢å¼ı
    -0.09
    POSITIVE LOGITS
    quake
    0.15
    worm
    0.14
    liness
    0.10
    wide
    0.10
    iness
    0.10
    ening
    0.10
    /or
    0.09
    çľĭä¸Ģä¸ĭ
    0.09
    walker
    0.09
    رز
    0.09
    Activations Density 0.014%

    No Known Activations