© 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. 20108
    Prev
    Next
    INDEX
    Explanations

    nasal cavity tissues

    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
    åŀĭåı·
    -0.10
    æĿİåħĪçĶŁ
    -0.10
    æ°´æĻ¶
    -0.10
    æĿ¾å¼Ľ
    -0.09
    对äºİæĪij们
    -0.09
    æ²®
    -0.09
    åįĬå²Ľ
    -0.08
    èĶ»
    -0.08
    mere
    -0.08
    æīij
    -0.08
    POSITIVE LOGITS
    ehr
    0.10
    å°ĸåı«
    0.09
    ClientId
    0.09
     Dow
    0.09
    åĭĩæ°Ķ
    0.09
    æĮ¤
    0.09
    åħ¬çº¦
    0.09
    å®ļä½į
    0.09
    æijĦ
    0.09
    ä¸įå¿ĺ
    0.09
    Activations Density 0.086%

    No Known Activations