© 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. 23141
    Prev
    Next
    INDEX
    Explanations

    goods and supplies

    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
    æĭĶ
    -0.10
    PRESSION
    -0.09
    æ½ľ
    -0.09
    åī¥ç¦»
    -0.09
     Leap
    -0.09
    æij¸
    -0.09
    éģĹåĿĢ
    -0.09
    Leap
    -0.08
    继
    -0.08
    ðŁİĻ
    -0.08
    POSITIVE LOGITS
     supplies
    0.12
    齿
    0.10
     Supplies
    0.10
    éĺ²çĸ«
    0.09
    å¼¹
    0.09
    éĩĩè´Ń
    0.09
    ortho
    0.09
    åĻ¨æ¢°
    0.09
    è´Ń
    0.08
    yc
    0.08
    Activations Density 0.036%

    No Known Activations