© 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. 51221
    Prev
    Next
    INDEX
    Explanations

    Ball, Z, Clark, krypton, Superpower

    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
    ç§ijæĬĢæĪIJæŀľ
    -0.09
    inch
    -0.09
    _gate
    -0.09
    odia
    -0.09
    สà¸Ļ
    -0.09
    Authorities
    -0.09
    ipel
    -0.09
    _SUBJECT
    -0.09
    çĸı
    -0.08
    æ´ģ
    -0.08
    POSITIVE LOGITS
     Jur
    0.10
    äºĪ
    0.09
     Ning
    0.09
    è¡ĮæĺŁ
    0.09
    æĹłæķĮ
    0.09
    èĭ£
    0.09
    ording
    0.09
    CLU
    0.09
    河西
    0.09
    å¼ģ
    0.08
    Activations Density 0.066%

    No Known Activations