© 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. 30765
    Prev
    Next
    INDEX
    Explanations

    volcanoes and geology

    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
    çĸ²åĬ³
    -0.11
    Leaf
    -0.09
    å±ŀ
    -0.09
    allah
    -0.09
    abad
    -0.09
    à¹ģà¸ĭ
    -0.09
    網
    -0.08
    游åĩ»
    -0.08
    ibia
    -0.08
    èĪ«
    -0.08
    POSITIVE LOGITS
    çģ«å±±
    0.19
     volcan
    0.15
     volcanic
    0.15
     volcano
    0.14
     eruption
    0.12
     lava
    0.12
     magma
    0.12
    æ³īæ°´
    0.11
     erupt
    0.11
    æ³ī
    0.11
    Activations Density 0.196%

    No Known Activations