© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21878
    Prev
    Next
    INDEX
    Explanations

    drilling bits and cutting hobbs

    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
    liness
    -0.10
    oft
    -0.08
    nel
    -0.08
    deo
    -0.08
    足迹
    -0.08
    ög
    -0.08
    ität
    -0.08
    楼主
    -0.07
    ä¿£
    -0.07
    æĢķ
    -0.07
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.13
    ached
    0.10
    åĮĹ大
    0.09
    ä¸Ĭãģ§
    0.09
    ifu
    0.09
    lessly
    0.09
    رس
    0.09
    èĽĨ
    0.09
    à¸Ĺà¸Ńà¸ĩ
    0.09
    bor
    0.09
    Activations Density 0.138%

    No Known Activations