© 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. 35241
    Prev
    Next
    INDEX
    Explanations

    allotment and allocation

    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
    hoot
    -0.10
    illion
    -0.10
    ly
    -0.09
    æĢį
    -0.09
    uan
    -0.09
    icky
    -0.09
    olist
    -0.08
    apore
    -0.08
    fur
    -0.08
    ulously
    -0.08
    POSITIVE LOGITS
     вÑĢемени
    0.10
    tee
    0.10
    estar
    0.10
    terior
    0.09
    侧ç»ĵæŀĦæĢ§
    0.09
    RARY
    0.09
    äºĨä¸Ģ份
    0.09
    tees
    0.09
    çıĬ
    0.09
    entric
    0.09
    Activations Density 0.022%

    No Known Activations