© 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. 17706
    Prev
    Next
    INDEX
    Explanations

    with the

    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
    çľ¼éĩĮ
    -0.10
    对æĸ¹
    -0.10
    imers
    -0.10
    æĺ¶
    -0.10
    jang
    -0.09
    å°įæĸ¹
    -0.09
    ipop
    -0.09
    POSIT
    -0.09
    æľīä»»ä½ķ
    -0.09
    ربÙĬ
    -0.09
    POSITIVE LOGITS
    ype
    0.09
    wf
    0.09
    度åģĩ
    0.08
    å¤ļåľ°
    0.08
    裳
    0.08
    æĢ¦
    0.08
    ENT
    0.08
    vo
    0.08
    ink
    0.08
     JO
    0.08
    Activations Density 0.063%

    No Known Activations