© 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. 17627
    Prev
    Next
    INDEX
    Explanations

    just how

    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
    atak
    -0.09
    å¼Ħ
    -0.09
    iel
    -0.08
    eper
    -0.08
    åİŁåĽłæĺ¯
    -0.08
    èĦ¾èĥĥ
    -0.08
     vö
    -0.08
    axon
    -0.08
     parti
    -0.08
    lösung
    -0.08
    POSITIVE LOGITS
    å¤ļä¹Ī
    0.19
    æľīå¤ļä¹Ī
    0.17
     how
    0.17
    æĺ¯å¤ļä¹Ī
    0.16
    å¦Ĥä½ķ
    0.16
     ìĸ¼ë§ĪëĤĺ
    0.16
    æľīå¤ļå°ij
    0.15
    æĺ¯å¦Ĥä½ķ
    0.13
    æĺ¯æĢİæł·
    0.12
    æľīå¤ļ大
    0.12
    Activations Density 0.079%

    No Known Activations