© 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. 35777
    Prev
    Next
    INDEX
    Explanations

    Jon followed by suffixes/names

    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
    ãģĹãģ¾ãģĦ
    -0.11
    ãģĹãģ¾
    -0.10
    eca
    -0.10
    ãģĹãģ¾ãģĨ
    -0.10
    urat
    -0.09
    ence
    -0.09
    年代
    -0.09
    eh
    -0.09
    خار
    -0.08
    -bodied
    -0.08
    POSITIVE LOGITS
    athon
    0.13
    sson
    0.10
    asz
    0.10
    ality
    0.10
    媳
    0.10
    ision
    0.10
    alysis
    0.09
    raph
    0.09
    icit
    0.09
    alleng
    0.09
    Activations Density 0.012%

    No Known Activations