© 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. 5011
    Prev
    Next
    INDEX
    Explanations

    coal and fuels

    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
    绣
    -0.10
    ä¸įä¸ĭ
    -0.09
    èįī
    -0.09
    æı¿
    -0.09
    æ¤Ĵ
    -0.09
     æŀ
    -0.09
    罩
    -0.09
    би
    -0.09
    çŀ©
    -0.09
    æŀľ
    -0.09
    POSITIVE LOGITS
    çħ¤
    0.18
     Coal
    0.16
    Coal
    0.15
     coal
    0.15
    çħ¤çĤŃ
    0.14
    å¼Ģéĩĩ
    0.14
    çħ¤çŁ¿
    0.13
    çĩĥçħ¤
    0.12
    coal
    0.12
    磸
    0.11
    Activations Density 0.053%

    No Known Activations