© 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. 50905
    Prev
    Next
    INDEX
    Explanations

    spatial prepositions and locations

    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
    æľªæĪIJ
    -0.11
    åIJĥçļĦ
    -0.10
    æĭĬ
    -0.10
    æŀķ
    -0.09
    Levels
    -0.09
     Vault
    -0.09
    çĭ®åŃIJ
    -0.08
    ocator
    -0.08
    pill
    -0.08
    å¿ĥä¸ŃçļĦ
    -0.08
    POSITIVE LOGITS
    æĿ¥æī¾
    0.10
    æĿ¥è®²
    0.09
    éĺŁéķ¿
    0.09
    acker
    0.09
    åłĤ
    0.09
     Portable
    0.08
    èĩªçĦ¶èĢĮ
    0.08
     amph
    0.08
    atalog
    0.08
    êm
    0.08
    Activations Density 0.088%

    No Known Activations