© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36475
    Prev
    Next
    INDEX
    Explanations

    abbreviations for units or types

    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
    aroo
    -0.10
    ect
    -0.09
    /or
    -0.09
    ster
    -0.09
    pins
    -0.09
    ste
    -0.09
    plier
    -0.08
    ulous
    -0.08
    lord
    -0.08
    JsonValue
    -0.08
    POSITIVE LOGITS
    amp
    0.10
    andard
    0.09
    udio
    0.09
    ngth
    0.09
    oll
    0.09
    æĥ³æĥ³
    0.09
    essler
    0.08
    åĵĤ
    0.08
    uset
    0.08
    æIJĢ
    0.08
    Activations Density 0.155%

    No Known Activations