© 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. 19566
    Prev
    Next
    INDEX
    Explanations

    how are you

    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
    éli
    -0.10
    oni
    -0.08
    è¾ī
    -0.08
    inel
    -0.08
    å¾ħãģ¡
    -0.08
    è¸Ĭè·ĥ
    -0.08
    emb
    -0.08
    缨
    -0.08
     Payne
    -0.07
    ä¸Ģè¾ĪåŃIJ
    -0.07
    POSITIVE LOGITS
    身ä½ĵåģ¥åº·
    0.14
    IAM
    0.11
    身å¿ĥåģ¥åº·
    0.11
     здоÑĢов
    0.11
    æģĻ
    0.11
    è¿ĺ好
    0.11
    å®ī康
    0.11
     здоÑĢовÑĮÑı
    0.11
    å¹³å®ī
    0.11
     health
    0.11
    Activations Density 0.049%

    No Known Activations