© 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. 29933
    Prev
    Next
    INDEX
    Explanations

    took home awards

    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
    ä¾ij
    -0.11
    &action
    -0.10
    nton
    -0.10
    åĽ·
    -0.09
    åľŁè±Ĩ
    -0.09
    .ERR
    -0.09
    容å¿į
    -0.09
    èĭ¹
    -0.08
     нек
    -0.08
    ornado
    -0.08
    POSITIVE LOGITS
    ests
    0.09
    çģ°
    0.09
    å¢ħ
    0.09
    lte
    0.09
    å¤ļä½ĻçļĦ
    0.09
    ç¥
    0.09
    第ä¸Ģæī¹
    0.09
    è¯Ŀè¯ŃæĿĥ
    0.08
    enum
    0.08
    top
    0.08
    Activations Density 0.006%

    No Known Activations