© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36214
    Prev
    Next
    INDEX
    Explanations

    car design and development

    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
    ä¼´
    -0.09
    ande
    -0.09
    èµĦæ·±
    -0.09
    åĬ£
    -0.08
    è¿ŀéĶģ
    -0.08
     vigil
    -0.08
    è´´è¿ij
    -0.08
    pose
    -0.08
    æľ¦
    -0.08
    æĬĬèĩªå·±
    -0.08
    POSITIVE LOGITS
    ç´§åĩij
    0.11
    æľºä½ĵ
    0.11
    åİ¢
    0.11
    设计
    0.11
    è¨Ńè¨Ī
    0.10
    çļĦ设计
    0.10
    åıijçĥ§
    0.10
    éĺħ读åħ¨æĸĩ
    0.10
     design
    0.10
     SPORT
    0.09
    Activations Density 0.218%

    No Known Activations