© 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. 30717
    Prev
    Next
    INDEX
    Explanations

    day night out

    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
    覺
    -0.09
    åŁºæľ¬ä¿¡æģ¯
    -0.09
    essed
    -0.09
    ancel
    -0.08
    缸å½ĵ
    -0.08
    eldon
    -0.08
    eed
    -0.08
    outer
    -0.08
    æĪĸå¤ļæĪĸå°ij
    -0.08
     Laden
    -0.08
    POSITIVE LOGITS
    让çĶ¨æĪ·
    0.10
    è¢
    0.10
    å·
    0.09
    èIJ½
    0.09
     Couple
    0.09
    -Ray
    0.09
    为æ°ij
    0.09
    èIJ½ä¸ĭ
    0.08
    hev
    0.08
    åĪ¶åº¦
    0.08
    Activations Density 0.024%

    No Known Activations