© 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. 33953
    Prev
    Next
    INDEX
    Explanations

    have to + verb

    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
    çĽ´è¾¾
    -0.10
    æ¡ħ
    -0.09
    åĩĢ
    -0.09
    PTR
    -0.09
    oby
    -0.09
    çĥŃçĪ±
    -0.08
    æŁ°
    -0.08
    çī¹æľīçļĦ
    -0.08
    俯
    -0.08
    _CP
    -0.08
    POSITIVE LOGITS
    éĹ®éĹ®
    0.09
     Brewing
    0.08
    缸å½ĵ
    0.08
    ä¸İä¼Ĺä¸įåIJĮ
    0.08
    ä¼łéĹ»
    0.08
    acco
    0.08
    好好
    0.08
    æĻ¤
    0.08
    actory
    0.08
    置身
    0.08
    Activations Density 0.021%

    No Known Activations