© 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. 58438
    Prev
    Next
    INDEX
    Explanations

    electrical connection, power, systems, machines, sockets

    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
    ed
    -0.10
    esh
    -0.10
    eward
    -0.10
    itory
    -0.10
    olas
    -0.10
    ellt
    -0.09
    arie
    -0.09
    olis
    -0.09
    ãĥĹãĥ©ãĤ¤
    -0.09
    exter
    -0.08
    POSITIVE LOGITS
    侯
    0.11
    ities
    0.11
    vin
    0.09
    iteDatabase
    0.09
    -symbol
    0.09
    çģ¾åĮº
    0.09
    gu
    0.09
    åŀŃ
    0.09
    åħ¬ç¤¾
    0.09
    teenth
    0.09
    Activations Density 0.032%

    No Known Activations