© 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. 7775
    Prev
    Next
    INDEX
    Explanations

    reception and receptionist

    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
    -0.10
    istic
    -0.09
    оÑģÑĮ
    -0.08
    å®ŀäºĭ
    -0.08
    mith
    -0.08
    stin
    -0.08
    å§Ķ书记
    -0.08
    adic
    -0.08
     önce
    -0.07
    ạt
    -0.07
    POSITIVE LOGITS
    ../../../
    0.15
    寤
    0.12
    acle
    0.11
    ../../
    0.10
    idas
    0.10
    ively
    0.10
    ortho
    0.10
    åŃº
    0.10
    eer
    0.10
    éĥĩ
    0.10
    Activations Density 0.029%

    No Known Activations