© 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. 2440
    Prev
    Next
    INDEX
    Explanations

    pharmacokinetics and disposition

    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
     honor
    -0.28
     cracks
    -0.28
    æļ´åĬĽ
    -0.27
     clim
    -0.27
     honors
    -0.26
     drill
    -0.26
     rebuilding
    -0.26
    зав
    -0.25
     clubs
    -0.25
    æ°ĶåĢĻ
    -0.24
    POSITIVE LOGITS
     kinetics
    0.40
    å³°åĢ¼
    0.35
     pharmac
    0.34
    èį¯çī©
    0.33
    allo
    0.32
     drug
    0.32
     dosage
    0.32
    èį¯
    0.31
    Peak
    0.31
    æ¯ĴæĢ§
    0.30
    Activations Density 0.536%

    No Known Activations