© 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. 23887
    Prev
    Next
    INDEX
    Explanations

    roller-coaster amusement rides

    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
    enance
    -0.11
    Ŀ
    -0.10
    ãģªãĤĬ
    -0.10
    .nlm
    -0.10
    ×ķת
    -0.10
    sız
    -0.09
    infeld
    -0.09
    alist
    -0.09
    tle
    -0.09
    ward
    -0.09
    POSITIVE LOGITS
    ized
    0.11
    è¹Ī
    0.10
    æĹ¶ä»£çļĦ
    0.09
    澡
    0.08
     Tat
    0.08
    izes
    0.08
    æĥķ
    0.08
    istics
    0.08
    妾
    0.08
    обÑĢ
    0.08
    Activations Density 0.007%

    No Known Activations