© 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. 22416
    Prev
    Next
    INDEX
    Explanations

    Wake Forest, WakeMed, County

    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
    fort
    -0.09
    antis
    -0.09
    itness
    -0.09
    æĩĭ
    -0.08
    æĭĪ
    -0.08
    _barrier
    -0.08
    æĦīå¿«
    -0.08
    eward
    -0.08
    顾éĹ®
    -0.08
     Pulitzer
    -0.08
    POSITIVE LOGITS
    wide
    0.10
    æħĪåĸĦ
    0.09
    åĩºåĵģ
    0.09
    åħļåĨħ
    0.09
    VPN
    0.08
    çIJ¨
    0.08
    æ·ĸ
    0.08
    iams
    0.08
    èĭ¦èĭ¦
    0.08
    éĤ¦
    0.08
    Activations Density 0.002%

    No Known Activations