© 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. 9727
    Prev
    Next
    INDEX
    Explanations

    dough products, nutty, kneading

    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
    ized
    -0.10
    ariat
    -0.10
    tered
    -0.09
    é£İåIJ¹
    -0.09
    onte
    -0.09
    ãĤĤãģĨ
    -0.08
    per
    -0.08
    orial
    -0.08
    ories
    -0.08
    TING
    -0.08
    POSITIVE LOGITS
    nuts
    0.13
    est
    0.11
    erty
    0.10
    sters
    0.10
    วย
    0.09
    iness
    0.09
    ze
    0.09
    åįģåħ«
    0.09
    dater
    0.09
    eneg
    0.09
    Activations Density 0.004%

    No Known Activations