© 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. 30812
    Prev
    Next
    INDEX
    Explanations

    Borg

    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
    æű
    -0.09
    6
    -0.09
    bread
    -0.08
    5
    -0.08
    éĨ®
    -0.08
    setSize
    -0.08
    åģļçļĦäºĭ
    -0.08
    解说
    -0.08
     bread
    -0.08
    ometer
    -0.08
    POSITIVE LOGITS
    çĪ¬
    0.11
    ÂĢÂ
    0.10
    è²¼
    0.09
    è¿Ń
    0.09
    çIJĨå·¥
    0.09
    è´´
    0.09
    å§Ŀ
    0.09
    嵬
    0.08
    áĢı
    0.08
    erset
    0.08
    Activations Density 0.004%

    No Known Activations