© 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. 3843
    Prev
    Next
    INDEX
    Explanations

    coating or applying a layer

    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
    cade
    -0.10
    éĶĻè¿ĩ
    -0.09
    orable
    -0.09
     оÑĤмеÑĤ
    -0.09
    æ±Ľ
    -0.09
    continued
    -0.09
    æĭĨ
    -0.08
    ettes
    -0.08
    éĥ½è®¤ä¸º
    -0.08
    AGIC
    -0.08
    POSITIVE LOGITS
    層
    0.15
    å±Ĥ
    0.14
    ä¸Ģå±Ĥ
    0.14
     layer
    0.13
    è¦Ĩ
    0.12
     layers
    0.12
    ç»Ĩèħ»
    0.10
     Layers
    0.10
    è¦ĨçĽĸ
    0.10
    çĽ¸äº²
    0.10
    Activations Density 0.247%

    No Known Activations