© 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. 6812
    Prev
    Next
    INDEX
    Explanations

    noun suffixes denoting quality or state

    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
    ness
    -0.12
    åĦ¿
    -0.12
    ings
    -0.12
    ify
    -0.11
    ing
    -0.11
    able
    -0.11
    inary
    -0.10
    ãģ¾ãģ¾
    -0.10
    lessly
    -0.10
    heits
    -0.10
    POSITIVE LOGITS
    åīįèĢħ
    0.11
    åįģ足
    0.11
    aho
    0.10
    ary
    0.10
     quo
    0.10
    xis
    0.09
    ми
    0.09
    tics
    0.09
    ellow
    0.09
    MLS
    0.09
    Activations Density 0.481%

    No Known Activations