© 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. 35569
    Prev
    Next
    INDEX
    Explanations

    invitations to interact

    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
    EMENT
    -0.09
    客æĪ·éľĢæ±Ĥ
    -0.09
    xC
    -0.08
    èŀ³
    -0.08
    ä¸įåħį
    -0.08
    LAB
    -0.08
    onna
    -0.08
     Nó
    -0.08
    lah
    -0.08
    ä¼ļ产çĶŁ
    -0.08
    POSITIVE LOGITS
    æŁIJ个
    0.10
    çļĦè¯Ŀ
    0.10
    ä»»ä½ķä¸Ģ个
    0.09
    uke
    0.09
    æľīä»»ä½ķ
    0.09
     further
    0.09
    ï¼Į请
    0.09
    æĽ´å¤ļä¿¡æģ¯
    0.09
    åĵªæĢķ
    0.09
    åħ·ä½ĵçļĦ
    0.09
    Activations Density 0.065%

    No Known Activations