© 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. 49333
    Prev
    Next
    INDEX
    Explanations

    is questions

    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
     deren
    -0.10
    缸åºĶçļĦ
    -0.09
    åĦĺ
    -0.08
    å®ĥæĺ¯
    -0.08
    æĬĬå®ĥ
    -0.08
    åıįèĢĮ
    -0.08
    å¾Ĺèµ·
    -0.08
    åĵªæĢķæĺ¯
    -0.08
     przecież
    -0.07
    é«®
    -0.07
    POSITIVE LOGITS
    ssel
    0.10
    𬣳
    0.10
    ofi
    0.09
    malink
    0.09
    æĦıæĢĿæĺ¯
    0.09
    å½ĵçĦ¶æĺ¯
    0.09
    etheless
    0.09
    __,__
    0.09
    ç½ij讯
    0.09
    @↵
    0.08
    Activations Density 1.309%

    No Known Activations