© 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. 50128
    Prev
    Next
    INDEX
    Explanations

    pharmacology, pharmacokinetics, pharmacodynamics

    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
    âĢ¾
    -0.09
    istic
    -0.09
    羶
    -0.09
    èĵī
    -0.08
     Rosen
    -0.08
    ifying
    -0.08
    bull
    -0.08
    anto
    -0.08
    åıĹåĪ°
    -0.08
    ÑĢож
    -0.08
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.10
    ally
    0.10
    åŃ¦å®¶
    0.09
    alia
    0.09
    æ§Ł
    0.09
    -pills
    0.09
    å¼Ī
    0.09
    raft
    0.09
    åĮºç®¡å§Ķä¼ļ
    0.09
    æ¯Ĵ
    0.09
    Activations Density 0.031%

    No Known Activations