© 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. 31243
    Prev
    Next
    INDEX
    Explanations

    filling gap or slot

    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
    çĹ¿
    -0.10
    dsl
    -0.09
    该æĿij
    -0.09
     Walton
    -0.09
    åĬ¡
    -0.09
    åĩıèĤ¥
    -0.08
    еÑĢж
    -0.08
    éľĸ
    -0.08
    å¥ķ
    -0.08
    åĭĻ
    -0.08
    POSITIVE LOGITS
     gaps
    0.12
    -gap
    0.11
    gap
    0.11
     gap
    0.11
    slot
    0.11
    åĨĴ
    0.10
     looph
    0.10
    åħħå®ŀ
    0.10
    åħħ
    0.09
    fill
    0.09
    Activations Density 0.068%

    No Known Activations