© 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. 60887
    Prev
    Next
    INDEX
    Explanations

    gasoline, petrol, fuel stations

    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
    Ware
    -0.10
    æ¼ıæ°´
    -0.10
    åĩºè¡Ģ
    -0.10
    åī¡
    -0.10
    lux
    -0.10
    åĪ¶éĢłä¸ļ
    -0.09
    èģĶåIJĪåĽ½
    -0.09
    dux
    -0.09
    举
    -0.09
    èĪī
    -0.09
    POSITIVE LOGITS
    汽油
    0.12
    ç«Ļéķ¿
    0.11
    åĬłæ²¹
    0.11
    æ²¹
    0.10
     petrol
    0.10
     gasoline
    0.10
    油价
    0.09
    çŁ³åĮĸ
    0.09
    çĩĥæ²¹
    0.09
    èĥŃ
    0.08
    Activations Density 0.071%

    No Known Activations