© 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. 22444
    Prev
    Next
    INDEX
    Explanations

    fossil fuel emissions and electricity generation

    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
    é¹ħ
    -0.08
    éļ½
    -0.08
    殿
    -0.08
     wholes
    -0.08
    å¾Ģ
    -0.08
    ä¸ĵå±ŀ
    -0.08
    _mB
    -0.08
    à¸Īร
    -0.08
    icus
    -0.08
     доÑģÑĤ
    -0.08
    POSITIVE LOGITS
    çĩĥçħ¤
    0.11
    å¤įæ´»
    0.10
    åĬ¨æijĩ
    0.10
    çĩĥçĥ§
    0.10
    顽强
    0.10
    åĮĸçŁ³
    0.09
    unky
    0.09
    çģ«åĬĽ
    0.09
     fossil
    0.09
    èĨ¨
    0.09
    Activations Density 0.047%

    No Known Activations