© 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. 64071
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    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
    ä¸įæŃ»
    -0.09
     tails
    -0.09
     ncols
    -0.09
    ling
    -0.09
    åĿIJçĿĢ
    -0.09
     Lease
    -0.09
    .prepend
    -0.08
    egt
    -0.08
    4
    -0.08
    skins
    -0.08
    POSITIVE LOGITS
     Vermont
    0.09
    森æŀĹ
    0.09
    åħ¼é¡¾
    0.09
    ç±į
    0.09
    incer
    0.09
     bite
    0.09
    çļĦ好å¤Ħ
    0.08
    _HAL
    0.08
    åĴ¬
    0.08
    ãĥĭãĥ¥
    0.08
    Activations Density 0.170%

    No Known Activations