© 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. 39813
    Prev
    Next
    INDEX
    Explanations

    Cosby Show, brew Equipment, orous liquid

    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
    onian
    -0.10
    Õ»
    -0.09
    atable
    -0.09
    èĬ±æł·
    -0.09
    èħĬ
    -0.09
     cardboard
    -0.09
    pong
    -0.09
     Packing
    -0.09
    inar
    -0.09
    anian
    -0.09
    POSITIVE LOGITS
    romo
    0.09
    å¤ļå¹´åīį
    0.09
    -bin
    0.09
    åľī
    0.08
     drill
    0.08
    æľīäºĽäºº
    0.08
    æīĵä»Ĺ
    0.08
    åĿıäºĭ
    0.08
    è´²
    0.08
     Rol
    0.08
    Activations Density 0.002%

    No Known Activations