© 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. 27598
    Prev
    Next
    INDEX
    Explanations

    speaking with others

    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
    колÑĮ
    -0.09
    ãģ¬
    -0.09
    èĢģ乡
    -0.09
    .remaining
    -0.09
    ä¸Ģåij³
    -0.08
    ãģ¨ãģĦãģ£ãģ¦
    -0.08
    åī©ä¸ĭ
    -0.08
    åħ¼ä»»
    -0.08
    è¾ħ导
    -0.08
    аÑģÑģив
    -0.08
    POSITIVE LOGITS
    éĻĮçĶŁ
    0.10
    ä¸Ģ群人
    0.10
    oman
    0.10
    åĪ«äººçļĦ
    0.10
     strangers
    0.10
    AccessType
    0.10
    éĻĮçĶŁäºº
    0.09
    ç»ĻåĪ«äºº
    0.09
    åįģåĩł
    0.09
    ä¸Ģ群
    0.09
    Activations Density 0.175%

    No Known Activations