© 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. 18323
    Prev
    Next
    INDEX
    Explanations

    choi, mckellar, patch, bug

    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
    举åįĹäºļ
    -0.10
    æ±°
    -0.10
    åĬ¨
    -0.10
    缮ãģ«
    -0.10
    QUOTE
    -0.09
    èĮĥ
    -0.09
    çĥľ
    -0.09
     bumps
    -0.09
    ricular
    -0.09
    详
    -0.09
    POSITIVE LOGITS
    è£ħéħį
    0.10
    åIJ¬å¾Ĺ
    0.09
    .poster
    0.09
     comm
    0.09
     hopeless
    0.08
    çIJĨä¼ļ
    0.08
    åħ¬çĽĬ
    0.08
    astery
    0.08
    aco
    0.08
     pal
    0.08
    Activations Density 0.298%

    No Known Activations