© 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. 22734
    Prev
    Next
    INDEX
    Explanations

    eric followed by names

    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
    -thirds
    -0.10
    -hearted
    -0.10
    æĤī
    -0.10
    æ®Ĩ
    -0.10
    /operator
    -0.09
    iez
    -0.09
     ведÑĮ
    -0.08
    edException
    -0.08
    à¸ķร
    -0.08
    liness
    -0.08
    POSITIVE LOGITS
    son
    0.16
    sson
    0.14
    aceous
    0.14
    sons
    0.11
    ament
    0.10
    lew
    0.10
    ìį¨
    0.09
    ron
    0.09
    ä¼ļè§īå¾Ĺ
    0.09
    ãģ¤ãģ®
    0.09
    Activations Density 0.011%

    No Known Activations