© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7156
    Prev
    Next
    INDEX
    Explanations

    -ing verbs

    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
    èĥŃ
    -0.10
    ä¸Ģ次次
    -0.10
    bia
    -0.09
     yaÅŁan
    -0.09
    roi
    -0.09
     наÑģел
    -0.08
    ahir
    -0.08
    oba
    -0.08
    rap
    -0.08
    tam
    -0.08
    POSITIVE LOGITS
    äºĽä»Ģä¹Ī
    0.10
    ä¸įéĶĻçļĦ
    0.09
    å¾Ĺå¾Ī
    0.09
    uts
    0.09
    èįª
    0.09
    å¾Ī好çļĦ
    0.09
    éĮ¾
    0.09
    ä»Ģä¹Īä¸ľè¥¿
    0.09
    é²²
    0.08
    ç¼ħ
    0.08
    Activations Density 0.171%

    No Known Activations