© 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. 38540
    Prev
    Next
    INDEX
    Explanations

    assemble and assembling

    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
    aceous
    -0.11
    าว
    -0.10
    bul
    -0.09
    Ñģл
    -0.09
    追究
    -0.09
    ened
    -0.08
    å¿«ä¸ī
    -0.08
    èĮĥæĸĩ
    -0.08
    inally
    -0.08
    -vars
    -0.08
    POSITIVE LOGITS
    ments
    0.11
    读åIJİ
    0.10
    ucha
    0.10
    nds
    0.10
    моÑĢ
    0.09
    pires
    0.09
     пÑĢавилÑĮно
    0.09
    mani
    0.08
    ri
    0.08
    د
    0.08
    Activations Density 0.034%

    No Known Activations