© 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. 17330
    Prev
    Next
    INDEX
    Explanations

    force and coercion

    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
    æĻº
    -0.10
    æĶ¹
    -0.09
    çĽĸ
    -0.09
    emit
    -0.08
    èĤĨ
    -0.08
     bout
    -0.08
     Sco
    -0.08
    ç«Ł
    -0.08
    对å¤ĸ
    -0.08
    .Depth
    -0.08
    POSITIVE LOGITS
    强迫
    0.30
    强åĪ¶
    0.30
    强è¡Į
    0.27
    éĢ¼
    0.18
    forced
    0.18
     forced
    0.18
     forcing
    0.18
    èĥģ
    0.17
     Forced
    0.17
     forcibly
    0.17
    Activations Density 0.107%

    No Known Activations