© 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. 5353
    Prev
    Next
    INDEX
    Explanations

    why can/should

    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
    YTE
    -0.09
    迸
    -0.08
    å¤ļæł·
    -0.08
    åijĬ
    -0.08
    åĬł
    -0.08
     Naz
    -0.08
    Tweet
    -0.08
    naz
    -0.08
    elta
    -0.08
    åħ³
    -0.08
    POSITIVE LOGITS
    èĥľä»»
    0.10
    ucker
    0.10
     convinced
    0.09
    为广大
    0.08
    æ·ij
    0.08
    ä¸Ģæľ¬
    0.08
    ä½ľä¸ºä¸ĢåIJį
    0.08
    æĶ¿æ²»
    0.08
    ilar
    0.08
    ä½ı宿
    0.08
    Activations Density 0.012%

    No Known Activations