© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51889
    Prev
    Next
    INDEX
    Explanations

    coordinate, coordination, coordinated

    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
    缴è¨Ģ
    -0.09
     negotiated
    -0.09
    kin
    -0.08
    éĺ³åı°
    -0.08
    ouro
    -0.08
    ãģ»ãģĨ
    -0.08
    饴
    -0.08
    abh
    -0.08
    ãģ¾ãģĻãģĮ
    -0.07
    æĪij们éľĢè¦ģ
    -0.07
    POSITIVE LOGITS
    ä¸Ģèĩ´
    0.12
    åįıè°ĥ
    0.11
    кÑĤ
    0.10
    èµ·æĿ¥
    0.10
    alar
    0.10
     ÑĥÑģили
    0.09
    çĶŁæŃ»
    0.09
    unn
    0.09
    .addObject
    0.09
    (coord
    0.09
    Activations Density 0.023%

    No Known Activations