© 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. 1939
    Prev
    Next
    INDEX
    Explanations

    phone, pager, and communication devices

    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
    rips
    -0.09
    æĺ¥ç§ĭ
    -0.09
    çħŀ
    -0.09
    å¤©çľŁ
    -0.09
    .ribbon
    -0.08
    åĮħè£ħ
    -0.08
    å¶Ļ
    -0.08
    强åĬ²
    -0.08
    .createComponent
    -0.08
    游
    -0.08
    POSITIVE LOGITS
    æīĭæľºåı·
    0.14
    æĭ¨æīĵ
    0.13
    æİ¥åIJ¬
    0.13
    åı·çłģ
    0.12
    çĶµè¯Ŀ
    0.10
    PHONE
    0.10
    çĥŃ线
    0.10
    æīĭæľº
    0.10
    æīĵçĶµè¯Ŀ
    0.09
    Vo
    0.09
    Activations Density 0.146%

    No Known Activations