© 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. 18918
    Prev
    Next
    INDEX
    Explanations

    Harry Potter characters and authors

    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
    esModule
    -0.08
    å¦ĤæĦı
    -0.08
    itus
    -0.08
    强åĬ²
    -0.08
    esimal
    -0.08
    èĬ«
    -0.08
    鲸
    -0.08
    åĹ£
    -0.08
    etal
    -0.08
    auer
    -0.08
    POSITIVE LOGITS
    æľīæīĢ
    0.11
    hev
    0.08
    ä¸Ģè§Ī
    0.08
    åĭĥ
    0.08
    opian
    0.08
     Gab
    0.08
    è¿Ļæł·
    0.08
    蹬
    0.08
    	rd
    0.08
    é¾Ļæ³ī
    0.08
    Activations Density 0.003%

    No Known Activations