© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23320
    Prev
    Next
    INDEX
    Explanations

    trucks or vehicles

    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
    ç§ī
    -0.10
    æĹħ
    -0.09
    声
    -0.09
    çĶµåŃIJ
    -0.09
    -column
    -0.09
    packing
    -0.09
    çĢij
    -0.08
    column
    -0.08
    íĥĦ
    -0.08
    èĬĤå¥ı
    -0.08
    POSITIVE LOGITS
    åħīèį£
    0.12
    è½½
    0.11
    æİ¥éĢģ
    0.10
    å·¡
    0.10
     duties
    0.10
    è¼ī
    0.10
    主è¦ģçĶ¨äºİ
    0.10
    -caret
    0.09
     duty
    0.09
    è¿IJéĢģ
    0.09
    Activations Density 0.145%

    No Known Activations