© 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. 6726
    Prev
    Next
    INDEX
    Explanations

    money and rewards

    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
    对æłĩ
    -0.10
    æľį
    -0.09
    çĽĺ
    -0.09
    жив
    -0.09
    æĹłæīĢ
    -0.09
    .Usage
    -0.08
    èŀįåĮĸ
    -0.08
    æ¢Ń
    -0.08
    éĻ·åħ¥äºĨ
    -0.08
    çłŃ
    -0.08
    POSITIVE LOGITS
    æĬ¥éħ¬
    0.31
    å¥ĸåĬ±
    0.24
    éħ¬
    0.24
     reward
    0.21
    reward
    0.20
    èĸªéħ¬
    0.20
     rewards
    0.19
     rewarded
    0.19
    èµļ
    0.19
    _reward
    0.19
    Activations Density 0.088%

    No Known Activations