© 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. 32348
    Prev
    Next
    INDEX
    Explanations

    drilling of wellbores

    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
    oblin
    -0.10
    èĢĢ
    -0.09
    迹
    -0.08
    åľ¨æĦı
    -0.08
    éĶ¦
    -0.08
    èĵĸ
    -0.08
    çĦ¦
    -0.08
    åľ¨å®¶éĩĮ
    -0.08
    æĥ³èµ·æĿ¥
    -0.08
    åľ¨å®¶
    -0.08
    POSITIVE LOGITS
    è´¯éĢļ
    0.10
    çªĦ
    0.09
    åĨĴéĻ©
    0.09
    åı°éĺ¶
    0.09
    ificate
    0.09
    æ¡ī
    0.09
    æłĪ
    0.09
    ãĤ«ãĥ³
    0.09
    æī¼
    0.09
    ERING
    0.09
    Activations Density 0.112%

    No Known Activations