© 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. 56171
    Prev
    Next
    INDEX
    Explanations

    patrol or patrolling

    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
    æĹłæ¯Ķ
    -0.10
    åıĸãĤĬ
    -0.09
    алÑĮн
    -0.09
    -grand
    -0.09
    åŁł
    -0.08
    lider
    -0.08
     gì
    -0.08
    hte
    -0.08
    çī¢
    -0.08
    æµģãĤĮ
    -0.08
    POSITIVE LOGITS
    gable
    0.11
    åijĺ
    0.11
    åĵ¡
    0.10
    ting
    0.10
    å·¡è§Ĩ
    0.09
    å·¡
    0.09
    æºĥ
    0.09
    cars
    0.09
    eurs
    0.09
     ÑĢоман
    0.09
    Activations Density 0.007%

    No Known Activations