© 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. 54710
    Prev
    Next
    INDEX
    Explanations

    roof rack, water heater, inverter

    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
    _ve
    -0.09
    į°
    -0.09
    æ´ĹåĩĢ
    -0.09
     PSU
    -0.09
    åĽĽå¤Ħ
    -0.08
    æĺ¼å¤ľ
    -0.08
     valide
    -0.08
    èĢĦ
    -0.08
    æį¢
    -0.08
    è°IJ
    -0.08
    POSITIVE LOGITS
    èĻŀ
    0.09
    çĥ§çĥ¤
    0.09
     anale
    0.08
    çľī
    0.08
    ç½®
    0.08
    æ¶Īè´¹èĢħçļĦ
    0.08
    åIJŁ
    0.08
    åĪł
    0.08
    ç¾ŀ
    0.08
    .appendTo
    0.08
    Activations Density 0.133%

    No Known Activations