© 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. 61696
    Prev
    Next
    INDEX
    Explanations

    made [some word]

    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
    çħ
    -0.10
    èµ°å¾Ĺ
    -0.10
    arness
    -0.09
    tá
    -0.09
    æĦī
    -0.09
    reas
    -0.09
    è¤Ĵ
    -0.08
    é«ĺæĸ°
    -0.08
    rice
    -0.08
     anth
    -0.08
    POSITIVE LOGITS
    omics
    0.09
     dies
    0.09
    楣
    0.09
    çĿĢæīĭ
    0.09
    emann
    0.08
    å¾Īéĩįè¦ģçļĦ
    0.08
     mention
    0.08
    æģ¶
    0.08
    æĺİç¡®
    0.08
    åĨ³å®ļ
    0.08
    Activations Density 0.042%

    No Known Activations