© 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. 6850
    Prev
    Next
    INDEX
    Explanations

    compelling or compelled action

    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
    rame
    -0.10
    ult
    -0.09
    ANGLES
    -0.08
    ä¸įçĶ¨æĭħå¿ĥ
    -0.08
    Compose
    -0.08
    иÑģк
    -0.08
    bread
    -0.08
     blown
    -0.08
    å®ļäºĨ
    -0.08
    icolor
    -0.08
    POSITIVE LOGITS
    ment
    0.14
    MENT
    0.12
    ìŀ¥ìĿĦ
    0.11
    ìĤ¬íķŃ
    0.11
    orsch
    0.10
    ément
    0.10
     nghiên
    0.10
    icit
    0.10
    æĪijçĪ±ä½ł
    0.09
    .gca
    0.09
    Activations Density 0.012%

    No Known Activations