© 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. 4103
    Prev
    Next
    INDEX
    Explanations

    lunchtime events

    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
    çļ¿
    -0.11
    ä½ıäºĨ
    -0.10
    enu
    -0.09
    主義
    -0.09
    arning
    -0.09
    大æłij
    -0.08
     иÑģкÑĥÑģ
    -0.08
    atis
    -0.08
    CHA
    -0.08
    é£İå°ļ
    -0.08
    POSITIVE LOGITS
    æŶèĬĤ
    0.11
    room
    0.10
    mate
    0.10
    maal
    0.10
    maid
    0.10
    ãĥ§ãĥ³
    0.09
    yard
    0.09
    rey
    0.09
    ery
    0.09
    opia
    0.09
    Activations Density 0.004%

    No Known Activations