© 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. 26612
    Prev
    Next
    INDEX
    Explanations

    police, patrol, RCMP, trooper

    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
    ä¸Ģ大åłĨ
    -0.08
    å¸Ĥéķ¿
    -0.08
    å¸ĤæĶ¿åºľ
    -0.08
    æľīä»Ģä¹Ī
    -0.08
    è¡į
    -0.08
     Edwards
    -0.08
    åħļæĶ¿
    -0.08
    æĬ¹
    -0.08
     progress
    -0.08
    Mayor
    -0.08
    POSITIVE LOGITS
    andles
    0.10
    ç®Ń
    0.10
    æĸ°é²ľ
    0.10
    .mount
    0.10
    å´§
    0.09
    çºłæŃ£
    0.09
    åħµåĽ¢
    0.09
    AILS
    0.09
    èģĶç½ij
    0.09
     Cave
    0.09
    Activations Density 0.010%

    No Known Activations