© 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. 11948
    Prev
    Next
    INDEX
    Explanations

    security, policy, rights, learning

    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
    uzzi
    -0.11
    ä¸įæĪIJ
    -0.10
    说起
    -0.09
    ä¸Ģç¯ĩ
    -0.09
    æ¡ij
    -0.09
    ần
    -0.09
    åīĶ
    -0.09
    ç²Ł
    -0.08
    æ§Ľ
    -0.08
    ä¸Ģ声
    -0.08
    POSITIVE LOGITS
     DPR
    0.09
    ä¹ĭéģĵ
    0.09
    ç¬
    0.08
    stoff
    0.08
    ogle
    0.08
     دائ
    0.08
    å°¤åħ¶æĺ¯
    0.08
    çŃł
    0.08
    é¾Ħ
    0.08
    å¤ļå¹´
    0.07
    Activations Density 0.244%

    No Known Activations