© 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. 55374
    Prev
    Next
    INDEX
    Explanations

    manner of correctness

    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
    باط
    -0.09
    æĢİèĥ½
    -0.09
    atch
    -0.09
    éļIJå½¢
    -0.08
    eres
    -0.08
    åºł
    -0.08
    è¿Ļä½į
    -0.08
     единÑģÑĤв
    -0.08
    æı¡æīĭ
    -0.08
    èľĥ
    -0.08
    POSITIVE LOGITS
    被èªī为
    0.11
    PELL
    0.10
    èIJ¥åķĨ
    0.10
    åľ°è¯´
    0.10
    被è¯Ħ为
    0.10
    被è§Ĩ为
    0.10
    满
    0.09
    被认为æĺ¯
    0.09
    åıijæĮ¥äºĨ
    0.09
    è¯łéĩĬ
    0.09
    Activations Density 0.023%

    No Known Activations