© 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. 7266
    Prev
    Next
    INDEX
    Explanations

    bash scripts

    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
    å¥Ķ
    -0.11
    èݺ
    -0.10
    鹫
    -0.10
    滹
    -0.10
    窦
    -0.09
    uit
    -0.09
    åĩºäºĨ
    -0.08
    åij½
    -0.08
    缸åħ³è´Łè´£
    -0.08
    angu
    -0.08
    POSITIVE LOGITS
    çĮĽçĥĪ
    0.09
    .sh
    0.09
    樽
    0.09
    ls
    0.08
    åł¡
    0.08
    ä¸Ģè§Ī
    0.08
    æģ¸
    0.08
    rig
    0.08
    ery
    0.08
     thảo
    0.08
    Activations Density 0.453%

    No Known Activations