© 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. 36271
    Prev
    Next
    INDEX
    Explanations

    Dell PowerEdge

    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
    ed
    -0.10
    edImage
    -0.09
    ly
    -0.09
    edly
    -0.09
    edList
    -0.09
    ä¼Ĭæĭī
    -0.09
    illo
    -0.09
    ãģ¶
    -0.08
    illis
    -0.08
    æ£
    -0.08
    POSITIVE LOGITS
    侬
    0.11
    æł¼å°Ķ
    0.09
    çıij
    0.09
    èĭ«
    0.09
    ÙĬÙĪÙĨ
    0.08
    æ²Ł
    0.08
    겨
    0.08
    ÑĥÑĩ
    0.08
    鬣
    0.08
    auce
    0.08
    Activations Density 0.003%

    No Known Activations