© 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. 32596
    Prev
    Next
    INDEX
    Explanations

    implementing and recreating based on examples

    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
    缶
    -0.10
    å¾ĢæĿ¥
    -0.10
    GED
    -0.09
    ä¹Łä¸įèĥ½
    -0.09
    èµ·èįī
    -0.09
    åĨ³èĥľ
    -0.08
     Perry
    -0.08
    æ¥ļ
    -0.08
    åģıåIJij
    -0.08
    楹
    -0.08
    POSITIVE LOGITS
    èĩªè¡Į
    0.11
    åĨįçİ°
    0.10
    å¤įåĪ¶
    0.10
    éĩįçİ°
    0.10
    åĽŀ家
    0.10
    æ¼Ķç»ĥ
    0.10
    èIJ½å®ŀ
    0.10
    å®ŀè·µ
    0.10
     reprodu
    0.10
    åĽŀåİ»
    0.10
    Activations Density 0.178%

    No Known Activations