© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37615
    Prev
    Next
    INDEX
    Explanations

    Crack and full version downloads

    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
    æĶ¶åĽŀ
    -0.11
    åģľä¸ĭ
    -0.10
    çļĦ家åºŃ
    -0.09
    æĸ°åĨłçĸ«æĥħ
    -0.09
    COVID
    -0.09
    éķ¿å¾ģ
    -0.09
     family
    -0.09
    family
    -0.08
    ãĥ§
    -0.08
    æī°
    -0.08
    POSITIVE LOGITS
    æļĹ
    0.10
    torrent
    0.10
    å®Įæķ´
    0.10
    çł´è§£
    0.09
    é«ĺæ¸ħ
    0.09
    æľĢæĸ°
    0.09
    åĶ§
    0.09
    ç®IJ
    0.09
    Mp
    0.08
    æī§æ³ķ
    0.08
    Activations Density 0.113%

    No Known Activations