© 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. 52592
    Prev
    Next
    INDEX
    Explanations

    Amounts followed by K

    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
    assel
    -0.10
     Stout
    -0.09
    agic
    -0.08
    æĢħ
    -0.08
    æķ°é¢Ŀ
    -0.08
    飬
    -0.08
    nad
    -0.08
    åĽłä¸ºæĪij
    -0.08
    enheim
    -0.08
     Fits
    -0.08
    POSITIVE LOGITS
    ponge
    0.09
    гÑĢан
    0.09
    æ³±
    0.09
    ilion
    0.09
    å©Ĩ
    0.09
    å¹´åīį
    0.09
    æµ·åĨħå¤ĸ
    0.09
    Recovered
    0.08
     Tw
    0.08
    onis
    0.08
    Activations Density 0.033%

    No Known Activations