© 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. 10034
    Prev
    Next
    INDEX
    Explanations

    do their job

    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
    imson
    -0.09
    éĢĶ
    -0.09
     Trials
    -0.09
    æľºéģĩ
    -0.08
     oppon
    -0.08
    çĥŃ线
    -0.08
    èѦ
    -0.08
    assi
    -0.08
    alar
    -0.08
    åĪ¤
    -0.08
    POSITIVE LOGITS
    èĩªè´¸
    0.08
    æµģæ°ĵ
    0.08
    ffset
    0.08
    åĿŀ
    0.08
    为èĩªå·±
    0.08
    å¿ĥä¸Ń
    0.08
    å®ŀè´¨æĢ§
    0.08
    æľīä¸Ģä½į
    0.08
    å©ī
    0.08
    .Dis
    0.08
    Activations Density 0.083%

    No Known Activations