© 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. 4436
    Prev
    Next
    INDEX
    Explanations

    wrestler claim

    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
    ä¸Ģè´¯
    -0.10
    æĿµ
    -0.09
    åİĨ
    -0.09
    UNCH
    -0.09
    acre
    -0.09
    缴è¨Ģ
    -0.09
    æĦļ
    -0.08
    STD
    -0.08
    onden
    -0.08
    CL
    -0.08
    POSITIVE LOGITS
    å®ĺ
    0.10
    çĪ»
    0.10
    è·¤
    0.10
    éĶ»
    0.09
     wrestler
    0.09
    澡
    0.09
    æķ°æį®æĺ¾ç¤º
    0.09
     Wrest
    0.09
    个å¤ļ
    0.09
     wrestlers
    0.09
    Activations Density 0.107%

    No Known Activations