© 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. 38719
    Prev
    Next
    INDEX
    Explanations

    to followed by verb

    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
    êt
    -0.10
    unately
    -0.10
    bidden
    -0.10
    .tm
    -0.10
     purposes
    -0.10
    ager
    -0.09
     sake
    -0.09
    è´»
    -0.09
    amen
    -0.09
    ró
    -0.09
    POSITIVE LOGITS
     for
    0.20
     длÑı
    0.16
     für
    0.16
    	for
    0.15
     voor
    0.15
    çĶ¨äºİ
    0.15
    对äºİ
    0.15
    for
    0.15
    ForKey
    0.15
     ÙĦÙĦ
    0.14
    Activations Density 0.545%

    No Known Activations