© 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. 47773
    Prev
    Next
    INDEX
    Explanations

    hose and tubing

    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
    çģ«çĥ§
    -0.10
    è¾ĥ大çļĦ
    -0.10
    ator
    -0.09
    ниÑĨ
    -0.09
    ANTE
    -0.09
    ante
    -0.09
    ê±°
    -0.09
    主æĦı
    -0.09
    rian
    -0.09
    éķĬ
    -0.09
    POSITIVE LOGITS
    pipe
    0.11
    esian
    0.09
    ä¸įå®Į
    0.09
    嵬
    0.09
    pipes
    0.09
    iggers
    0.08
    bags
    0.08
    ernet
    0.08
    ðŁı»
    0.08
    ä¸ĢåĽŀäºĭ
    0.08
    Activations Density 0.016%

    No Known Activations