© 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. 4391
    Prev
    Next
    INDEX
    Explanations

    educational intervention

    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®īå®ļ
    -0.11
    æĺ¯ä½ł
    -0.10
    èµĸ以çĶŁåŃĺ
    -0.10
    æĹħ游度åģĩ
    -0.10
    客è§Ĥ
    -0.09
    isci
    -0.09
    axed
    -0.09
    /loader
    -0.09
    steen
    -0.09
    åŁºåĩĨ
    -0.09
    POSITIVE LOGITS
    å¹²é¢Ħ
    0.13
     intervention
    0.11
     interventions
    0.09
    çĭĻ
    0.09
    åĪ°è´¦
    0.09
    ä¸ĬéŨ
    0.09
    æıIJé«ĺ
    0.09
    æıIJé«ĺäºĨ
    0.08
    æݪæĸ½
    0.08
    æĶ¹åĸĦ
    0.08
    Activations Density 0.459%

    No Known Activations