© 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. 47752
    Prev
    Next
    INDEX
    Explanations

    if else structure

    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
    å¦Ĥæŀľæ²¡æľī
    -0.11
    iface
    -0.10
     ведÑĮ
    -0.10
    à¹Ĥà¸Ľà¸£à¸Ķ
    -0.10
    fuse
    -0.10
    å¦Ĥæŀľä¸įæĺ¯
    -0.10
    ifle
    -0.10
    åĵĩ
    -0.09
    глав
    -0.09
    å¦Ĥæŀľæľī
    -0.09
    POSITIVE LOGITS
    rames
    0.21
    /how
    0.14
    rame
    0.12
    empre
    0.11
    eatures
    0.11
    fy
    0.11
    ramework
    0.10
    loat
    0.10
    -ever
    0.10
    eel
    0.10
    Activations Density 0.162%

    No Known Activations