© 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. 62416
    Prev
    Next
    INDEX
    Explanations

    canned goods and food cans

    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
    edom
    -0.09
    éļĪ
    -0.09
    iano
    -0.09
    usz
    -0.08
    .IsSuccess
    -0.08
    å´Ń
    -0.08
    ialis
    -0.08
     меÑģÑĤа
    -0.08
    umph
    -0.08
    .sam
    -0.08
    POSITIVE LOGITS
    åĭī
    0.10
    ning
    0.09
    orro
    0.09
    ellation
    0.09
     chá»ĭu
    0.08
    禧
    0.08
    大çīĩ
    0.08
    åİĤ
    0.08
    åĩĮ
    0.08
    é¹Ĺ
    0.08
    Activations Density 0.011%

    No Known Activations