© 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. 38059
    Prev
    Next
    INDEX
    Explanations

    Car, chlor, burn, sab, lib, du, cub, east

    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
    _CLI
    -0.10
    æī§
    -0.09
    轶
    -0.09
    主è¦ģæľī
    -0.08
     AFL
    -0.08
    zig
    -0.08
    æݨåIJij
    -0.08
    å¦Ĥä¸ĭ
    -0.08
    åĪĨæĪIJ
    -0.08
    owered
    -0.08
    POSITIVE LOGITS
    ÑĢей
    0.10
    æĪijèĩªå·±
    0.10
    ä¹Łå¥½
    0.09
    缯
    0.09
    TagName
    0.09
    éĤ£è¾¹
    0.08
    egt
    0.08
    oru
    0.08
    obi
    0.08
    æ¡ĪåŃIJ
    0.08
    Activations Density 0.114%

    No Known Activations