© 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. 33300
    Prev
    Next
    INDEX
    Explanations

    proud of

    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
     Rosenberg
    -0.10
    è¦ģæ±Ĥ
    -0.09
    人群ä¸Ń
    -0.09
    çĪ½
    -0.09
    ç»Ń
    -0.09
    çĶŁåij½çļĦ
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.08
     vô
    -0.08
     overs
    -0.08
     Celt
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.13
    çĬ¹
    0.09
    ä»Ĺ
    0.08
    åİŁæĸĩåľ°åĿĢ
    0.08
    è¢«åĽ°
    0.08
    eld
    0.08
     milit
    0.08
    é¢ģ
    0.08
    è¿ĻçĤ¹
    0.08
    个æĢ§
    0.08
    Activations Density 0.007%

    No Known Activations