© 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. 29928
    Prev
    Next
    INDEX
    Explanations

    cyclops, telomerase, genetic, morphogenetic

    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
     Ñĥзн
    -0.10
    isz
    -0.10
    èĬľ
    -0.09
    æĹłçŁ¥
    -0.09
    忧èĻij
    -0.09
    lander
    -0.09
    éŨçªĹ
    -0.09
    çij°
    -0.09
    ucken
    -0.09
    .tk
    -0.09
    POSITIVE LOGITS
    åĨĮ
    0.11
    oms
    0.09
    çĶ¨åĵģ
    0.08
    å¾µ
    0.08
    箧
    0.08
     amps
    0.08
    èħ®
    0.08
    fore
    0.08
    è£ģåĪ¤
    0.08
     contingent
    0.08
    Activations Density 0.008%

    No Known Activations