© 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. 4558
    Prev
    Next
    INDEX
    Explanations

    transactions, bids, filing, approval

    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
    hop
    -0.11
    å¼ĵ
    -0.08
     hop
    -0.08
    觥
    -0.08
    arks
    -0.08
    /problems
    -0.08
    stamp
    -0.08
    空
    -0.08
    catid
    -0.08
    UM
    -0.08
    POSITIVE LOGITS
    ITTER
    0.11
    裱
    0.10
    寨
    0.10
    æĶ¶è´Ń
    0.09
     sez
    0.09
    çĶĺ
    0.09
    è¶ħé¢Ŀ
    0.09
    åħĪ导
    0.09
    å¾ģéĽĨ
    0.09
    èĥ¯
    0.09
    Activations Density 0.026%

    No Known Activations