© 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. 32805
    Prev
    Next
    INDEX
    Explanations

    going 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
    å®ŀåľ¨æĺ¯
    -0.11
    ä¹ĭåĬĽ
    -0.10
    åħ¬çº¦
    -0.09
    çļĦä¸Ģéĥ¨åĪĨ
    -0.09
    à¹ĥà¸Ļà¸ģาร
    -0.09
    åĪĹ为
    -0.09
    åıĪ好åıĪ
    -0.09
    è¿Ļæīį
    -0.08
    çľĭè¿ĩ
    -0.08
    ãģĦãģĨ
    -0.08
    POSITIVE LOGITS
    eres
    0.09
    aran
    0.08
     Fame
    0.08
    åĽłæѤ
    0.08
    idebar
    0.08
    æĿı
    0.08
    ëģĶ
    0.08
    iants
    0.08
    olin
    0.08
     prose
    0.08
    Activations Density 0.013%

    No Known Activations