© 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. 61624
    Prev
    Next
    INDEX
    Explanations

    Lockheed, Berkshire, Warren

    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
    åļ£
    -0.10
    fulness
    -0.10
    循
    -0.09
    åĬŀåѦ
    -0.09
    ewise
    -0.09
    fully
    -0.08
    ajor
    -0.08
     Ub
    -0.08
    blur
    -0.08
    ĺ认
    -0.08
    POSITIVE LOGITS
    imat
    0.10
    nga
    0.09
    è¶³å¤Ł
    0.09
    pret
    0.09
    åħ¬å¹³
    0.09
    å¨ĺ
    0.08
    InstanceState
    0.08
    traction
    0.08
    åĢ¾
    0.08
     Nä
    0.08
    Activations Density 0.002%

    No Known Activations