© 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. 39770
    Prev
    Next
    INDEX
    Explanations

    dispose of waste or trash

    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
    çĦ¦
    -0.10
    ugins
    -0.10
    çĻ¾
    -0.09
    egl
    -0.09
    ymph
    -0.09
    çıł
    -0.09
    éĢīåĩº
    -0.09
    FRING
    -0.09
    gems
    -0.08
    ä¸į大
    -0.08
    POSITIVE LOGITS
     disposal
    0.16
     Dispose
    0.14
     dispose
    0.13
    dispose
    0.13
    åŀĥåľ¾æ¡¶
    0.13
    Dispose
    0.13
     disposing
    0.12
    å¤Ħç½®
    0.12
    åŀĥåľ¾
    0.11
     disposed
    0.11
    Activations Density 0.097%

    No Known Activations