© 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. 17737
    Prev
    Next
    INDEX
    Explanations

    explosions at locations

    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
    é£Łæ¬²
    -0.09
    çģ«çĥ§
    -0.09
    TRAN
    -0.08
    åģľè½¦ä½į
    -0.08
    éĢģåĪ°
    -0.08
    æĬĹæ°§åĮĸ
    -0.07
    çĥ·
    -0.07
    åĥ»
    -0.07
    tic
    -0.07
    orio
    -0.07
    POSITIVE LOGITS
     distr
    0.10
    ç¦ıå¾·
    0.10
    Filled
    0.10
    æĹĦ
    0.09
    ByVersion
    0.09
    夤
    0.09
    两年åīį
    0.09
    姮
    0.09
    filled
    0.09
    棻
    0.09
    Activations Density 0.095%

    No Known Activations