© 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. 19555
    Prev
    Next
    INDEX
    Explanations

    dual licensed or dual purpose

    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
    د
    -0.08
    oved
    -0.08
    dc
    -0.08
    ãĤ½ãĥ³
    -0.07
    èĶĵ
    -0.07
    åIJĥé¥Ń
    -0.07
    udas
    -0.07
    doc
    -0.07
    ech
    -0.07
    fers
    -0.07
    POSITIVE LOGITS
    itarian
    0.12
    ityEngine
    0.11
    nda
    0.11
    istically
    0.11
    istic
    0.10
    -track
    0.10
    ided
    0.10
    æĪĸå¤ļ
    0.10
    ities
    0.10
    -purpose
    0.10
    Activations Density 0.024%

    No Known Activations