© 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. 7199
    Prev
    Next
    INDEX
    Explanations

    oil and gas production

    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
    硬åĮĸ
    -0.10
    å´¦
    -0.09
    箬
    -0.09
    åħĶ
    -0.08
    .Bitmap
    -0.08
    æĿĨèıĮ
    -0.08
    Bullet
    -0.08
    æ»ĭåij³
    -0.08
    æĸ©
    -0.08
    lander
    -0.08
    POSITIVE LOGITS
    æ²¹æ°Ķ
    0.21
    çŁ³æ²¹
    0.21
     oil
    0.21
    æ²¹çĶ°
    0.21
    åİŁæ²¹
    0.20
    oil
    0.19
    æ²¹
    0.18
    Oil
    0.18
     اÙĦÙĨÙģØ·
    0.17
     Oil
    0.17
    Activations Density 0.205%

    No Known Activations