© 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. 57218
    Prev
    Next
    INDEX
    Explanations

    nor, neither, do not

    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
     zwar
    -0.11
    ä¸įä»ħè¦ģ
    -0.10
    ä¸įä»ħ
    -0.09
     both
    -0.09
    ä¹Łæľī
    -0.08
    身
    -0.08
    jis
    -0.08
    avic
    -0.08
    ä¸įä½Ĩ
    -0.08
    urn
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.15
    å¯¹æľªæĿ¥
    0.11
    ä¹Łä¸įåı¯èĥ½
    0.11
     stint
    0.11
    ä¾ĭå¤ĸ
    0.10
    çIJĨä¼ļ
    0.10
    ä¸Ŀ毫
    0.10
    èļĢ
    0.10
    åħ¶ä»ĸçļĦ
    0.10
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.10
    Activations Density 0.025%

    No Known Activations