© 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. 3093
    Prev
    Next
    INDEX
    Explanations

    castle or palace

    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
    æĭį
    -0.09
    .inline
    -0.09
    èĥ«
    -0.09
     Flood
    -0.09
     Gallagher
    -0.09
     fertil
    -0.09
    ertil
    -0.08
    bands
    -0.08
    anke
    -0.08
    åħ¨å¸Ĥ
    -0.08
    POSITIVE LOGITS
    åŁİåł¡
    0.16
    宫殿
    0.15
     castle
    0.13
    宫
    0.12
    座
    0.11
    çļĩ宫
    0.10
    åł¡åŀĴ
    0.10
    豪å®ħ
    0.10
     Castle
    0.10
     fortress
    0.10
    Activations Density 0.117%

    No Known Activations