© 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. 34168
    Prev
    Next
    INDEX
    Explanations

    indicated or in

    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
    ä¸İæŶ
    -0.09
    çĭł
    -0.08
    æĸ¯
    -0.08
    allet
    -0.08
    åłĨ
    -0.08
     Retreat
    -0.08
    æĩĭ
    -0.08
    ç½ij讯
    -0.08
    nia
    -0.08
    æĭīæĸ¯
    -0.08
    POSITIVE LOGITS
    绩
    0.10
    _accessible
    0.10
    第ä¸Ģ家
    0.10
    arus
    0.10
    å½ķçĶ¨
    0.10
    å½ĵä¹ĭ
    0.10
    éķ¿éķ¿
    0.09
    åħ¬çĶ¨
    0.09
    idar
    0.09
    aroo
    0.09
    Activations Density 0.052%

    No Known Activations