© 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. 20179
    Prev
    Next
    INDEX
    Explanations

    Swayne, well, ray, swelled, haul

    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
    ization
    -0.10
    ized
    -0.10
    åĮĸçļĦ
    -0.10
    mas
    -0.09
    vier
    -0.09
    iss
    -0.09
    sla
    -0.08
    ç¯ĵ
    -0.08
    zos
    -0.08
    ìĥī
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
    utdown
    0.10
    å¾Ĺä½ı
    0.10
    缱
    0.10
    æĴ¼
    0.10
    å½ĵä¹ĭ
    0.10
    ustin
    0.10
    breaker
    0.09
    enance
    0.09
    stakes
    0.09
    Activations Density 0.004%

    No Known Activations