© 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. 58350
    Prev
    Next
    INDEX
    Explanations

    corporate responsibility and sustainability

    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
    妹
    -0.08
    .ascii
    -0.08
    ç´¯
    -0.08
     Butter
    -0.08
    æľīéĻIJ
    -0.08
    æľ«
    -0.08
    äºļè¿IJ
    -0.08
     Ari
    -0.08
    对该
    -0.08
    dot
    -0.08
    POSITIVE LOGITS
    CSR
    0.11
    ä¼ģä¸ļåľ¨
    0.10
    èij£äºĭä¼ļ
    0.10
    åħ¬åı¸åľ¨
    0.10
    伦çIJĨ
    0.10
    éģĵå¾·
    0.10
     CSR
    0.09
    _INLINE
    0.09
    å±¥è¡Į
    0.09
    ç¾İèªī
    0.09
    Activations Density 0.086%

    No Known Activations