© 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. 16853
    Prev
    Next
    INDEX
    Explanations

    relationship between concepts

    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
    å¾½
    -0.09
    æ±ģ
    -0.09
    åIJ²
    -0.08
     giác
    -0.08
    æĶĢ
    -0.08
    _COMPILER
    -0.08
    æīĢèĥ½
    -0.08
    HeaderText
    -0.08
     Porno
    -0.08
    æĸĹ
    -0.07
    POSITIVE LOGITS
    çļĦæĢģ度
    0.11
    REEN
    0.10
    çļĦæĦŁæĥħ
    0.09
    åŃIJ女
    0.09
    çļĦæł¹æľ¬
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
     окÑĢÑĥжа
    0.09
    åij¨åĽ´
    0.09
    åħ¶ä»ĸ人
    0.09
    åħ¶ä»ĸ
    0.09
    Activations Density 0.090%

    No Known Activations