© 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. 2222
    Prev
    Next
    INDEX
    Explanations

    seen a or determiner

    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
    æŃ¥åħ¥
    -0.10
    orro
    -0.10
    iage
    -0.09
    ernals
    -0.09
    emens
    -0.09
    gere
    -0.09
    è¢Ī
    -0.09
    妹
    -0.08
    isoft
    -0.08
    eners
    -0.08
    POSITIVE LOGITS
    theless
    0.11
    ning
    0.10
    rather
    0.10
    ality
    0.10
    å¯Ł
    0.09
    ä¸Ģå¹ķ
    0.09
    æľīçļĦ
    0.09
     firsthand
    0.08
    èĩªåĬ©
    0.08
    ials
    0.08
    Activations Density 0.020%

    No Known Activations