© 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. 19892
    Prev
    Next
    INDEX
    Explanations

    reserve

    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
    ../../../
    -0.14
    ting
    -0.10
    ãĥ³ãĤ°
    -0.10
    ly
    -0.09
    踪
    -0.09
    ../../../../
    -0.09
    fa
    -0.09
    fas
    -0.08
    uality
    -0.08
    ValueType
    -0.08
    POSITIVE LOGITS
    oftware
    0.11
    igel
    0.11
    ãģ¾ãģ¾
    0.10
    .mozilla
    0.09
    igid
    0.09
    ocity
    0.09
    éĽĦåİļ
    0.09
    lector
    0.09
    iland
    0.09
    egin
    0.08
    Activations Density 0.009%

    No Known Activations