© 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. 7416
    Prev
    Next
    INDEX
    Explanations

    meaningful | substantial | professional

    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
    needle
    -0.09
     drafts
    -0.09
    åĥ³
    -0.08
    lights
    -0.08
    çĶ³
    -0.08
    èĪĮ
    -0.08
    èħ¿éĥ¨
    -0.08
    atee
    -0.08
    /python
    -0.08
    /T
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.13
    æľīæĦıä¹ī
    0.11
    羣æŃ£
    0.11
    çļĦéĩį大
    0.10
    常æĢģ
    0.10
    è§Ħ模åĮĸ
    0.10
    大è§Ħ模
    0.10
    ä¹ł
    0.10
    æŃ£å¼ı
    0.10
    主æµģ
    0.10
    Activations Density 0.251%

    No Known Activations