© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37982
    Prev
    Next
    INDEX
    Explanations

    pressure controller or pressure treatment

    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
    ry
    -0.11
    ships
    -0.10
    èĩ³äºİ
    -0.09
    ue
    -0.09
    utz
    -0.09
    ness
    -0.09
    avigation
    -0.09
    nas
    -0.09
    ship
    -0.09
    agraph
    -0.09
    POSITIVE LOGITS
     cooker
    0.11
    onom
    0.10
    åįģ足
    0.10
    èĮ¸
    0.10
    isel
    0.09
    æĦŁ
    0.09
    edList
    0.09
    人éĢī
    0.09
    леж
    0.08
    geber
    0.08
    Activations Density 0.043%

    No Known Activations