© 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. 50610
    Prev
    Next
    INDEX
    Explanations

    actions often followed by prepositions

    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
    çĿ
    -0.09
    à¹Ģà¸ī
    -0.09
    _bd
    -0.09
    iting
    -0.09
    lug
    -0.09
    ongan
    -0.08
    ä»Ģä¹Īä¸ľè¥¿
    -0.08
    ogra
    -0.08
    è°
    -0.08
    ç»ıçIJĨ
    -0.08
    POSITIVE LOGITS
    æľ¬äºº
    0.11
    å½»
    0.11
    æľ¬æľŁ
    0.10
    æŁĺ
    0.09
     behalf
    0.09
    OrDefault
    0.09
    aved
    0.08
    æ³Į
    0.08
    ÑĩÑĮ
    0.08
    obb
    0.08
    Activations Density 0.107%

    No Known Activations