© 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. 34930
    Prev
    Next
    INDEX
    Explanations

    movement, travel, migration

    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
    å²ļ
    -0.09
    缨
    -0.09
    reo
    -0.09
    æijĬ
    -0.09
    缺åı£
    -0.09
    rado
    -0.09
    æĶ¾å¼ĥäºĨ
    -0.09
    _ve
    -0.09
    èŀį
    -0.08
    æ©Ľ
    -0.08
    POSITIVE LOGITS
    ç©¿è¿ĩ
    0.11
    æĬļ
    0.10
    移åĬ¨
    0.10
    along
    0.09
     пеÑĢем
    0.09
    ORY
    0.09
    ç¼ĵæħ¢
    0.09
    èµ°è¿ĩ
    0.09
    ç©¿è¶Ĭ
    0.09
    å¾Ĭ
    0.09
    Activations Density 0.271%

    No Known Activations