© 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. 62819
    Prev
    Next
    INDEX
    Explanations

    repeat or duplicate elements

    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
    ignment
    -0.10
    æķĻä¼ļ
    -0.09
    èĢģ乡
    -0.09
    NES
    -0.09
    oria
    -0.09
    orsk
    -0.09
    lij
    -0.08
    èŃĺ
    -0.08
    ç½ķ
    -0.08
    rios
    -0.08
    POSITIVE LOGITS
    ä¸Ģéģį
    0.12
    äºĨä¸Ģéģį
    0.11
    åīįä¸ĸ
    0.11
    说è¿ĩ
    0.09
    åĩºèī²
    0.08
    ç¥ļ
    0.08
    åĸľ
    0.08
    dle
    0.08
     Slate
    0.08
    棫
    0.08
    Activations Density 0.083%

    No Known Activations