© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9415
    Prev
    Next
    INDEX
    Explanations

    api usage and errors

    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
    æ¿¡
    -0.11
    hör
    -0.10
    线ä¸Ĭ
    -0.09
    æī«
    -0.09
    컬
    -0.09
    éĻµ
    -0.08
    setter
    -0.08
    顾
    -0.08
    icare
    -0.08
    SURE
    -0.08
    POSITIVE LOGITS
    åĪļæīį
    0.10
    åĩıè½»
    0.10
    æĬ½åıĸ
    0.10
    æ³ķå¾ĭ顾éĹ®
    0.09
    æĿ¯åŃIJ
    0.09
    -json
    0.09
     Cup
    0.09
    åĬłéĩį
    0.09
    ç¼£
    0.08
     JSON
    0.08
    Activations Density 0.229%

    No Known Activations