© 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. 55946
    Prev
    Next
    INDEX
    Explanations

    publications and references

    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
    åij½
    -0.11
    æĪĸå¤ļ
    -0.09
    æľ¬ç«Ļ
    -0.09
    ulan
    -0.09
    çł»
    -0.09
    ç»ĩ
    -0.08
    mlin
    -0.08
    åĿIJ
    -0.08
    åıijéŁ³
    -0.08
    篱
    -0.08
    POSITIVE LOGITS
    èĪĨ
    0.09
    ä¸Ģ个个
    0.09
    äºĭ
    0.09
     вÑģÑı
    0.09
    æ·¡åĮĸ
    0.09
    è¯Ħè®®
    0.08
    轻轻
    0.08
    asz
    0.08
    äºĭãģĮ
    0.08
    æĮĩ导æĦıè§ģ
    0.08
    Activations Density 0.087%

    No Known Activations