© 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. 20222
    Prev
    Next
    INDEX
    Explanations

    SDWebImage, S-Space, Soot, Saravan

    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
    uar
    -0.10
    顺德
    -0.10
    ĸ
    -0.10
    erv
    -0.10
    stock
    -0.09
    ihan
    -0.09
    سÙĨ
    -0.09
    umen
    -0.09
     sheer
    -0.09
    anche
    -0.09
    POSITIVE LOGITS
    ftware
    0.18
    wich
    0.14
    -called
    0.14
    pher
    0.12
    writers
    0.12
    oner
    0.12
    ificance
    0.12
    ellite
    0.12
    emens
    0.12
    quence
    0.11
    Activations Density 2.324%

    No Known Activations