© 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. 18509
    Prev
    Next
    INDEX
    Explanations

    Sheffield Wednesday

    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
    ÌĢ
    -0.09
    骧
    -0.09
    çı°
    -0.09
    缮ãģ®
    -0.08
    OSH
    -0.08
    grab
    -0.08
    cheme
    -0.08
    quat
    -0.08
    addtogroup
    -0.08
    jÄħ
    -0.08
    POSITIVE LOGITS
    ÙĪØ®
    0.11
    ilder
    0.10
    ÙĬÙĥ
    0.10
    ÑĥÑħ
    0.10
    ields
    0.09
    çĶ¨åĵģ
    0.09
    ishly
    0.09
    ers
    0.09
    åŁŃ
    0.09
    åģľçķĻåľ¨
    0.09
    Activations Density 0.013%

    No Known Activations