© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1474
    Prev
    Next
    INDEX
    Explanations

    nucleus accumbens reward pathway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     kir
    -0.28
     unread
    -0.27
     tensions
    -0.25
    åı°é£İ
    -0.25
     Incident
    -0.23
     newsletters
    -0.23
     fortn
    -0.23
    尺寸
    -0.22
    undefined
    -0.22
    çŃ¥
    -0.22
    POSITIVE LOGITS
     reward
    0.40
     Reward
    0.35
     addictive
    0.32
     dopamine
    0.30
    诱æĥij
    0.30
     Rewards
    0.29
    æľºåĪ¶
    0.28
     Gambling
    0.28
     rewards
    0.28
    åħ´å¥ĭ
    0.28
    Activations Density 0.096%

    No Known Activations