© 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. 17251
    Prev
    Next
    INDEX
    Explanations

    arrival and departure

    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
    åħ¨åľº
    -0.09
    abis
    -0.09
    _emit
    -0.09
    éĥ¢
    -0.09
     simul
    -0.09
     qw
    -0.09
    让å®ĥ
    -0.09
    åIJijåīį
    -0.08
    è¢Ħ
    -0.08
    zos
    -0.08
    POSITIVE LOGITS
     arrivals
    0.10
     arrival
    0.10
    odi
    0.09
     Arrival
    0.09
    ORMAT
    0.09
    ITH
    0.09
    å½ĵæĻļ
    0.09
    æ·ĸ
    0.09
     arrive
    0.09
    odate
    0.08
    Activations Density 0.050%

    No Known Activations