© 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. 56847
    Prev
    Next
    INDEX
    Explanations

    Absinthe, tequila, fructose

    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
    fab
    -0.10
    edic
    -0.08
     Fab
    -0.08
    æ¯Ķäºļ
    -0.08
     обоÑĢ
    -0.08
    å¸ĥå±Ģ
    -0.08
    izzer
    -0.08
    cem
    -0.08
    对å¾ħ
    -0.07
    ement
    -0.07
    POSITIVE LOGITS
    æ¡Ģ
    0.11
    allis
    0.10
    è¿Ļæł·ä¸Ģ个
    0.09
    owitz
    0.09
    åħ»èĤ²
    0.09
    åŁŃ
    0.09
    ä¸į失
    0.09
    ç»ıæµİå¢ŀéķ¿
    0.09
    anner
    0.09
    å®ī举
    0.09
    Activations Density 0.004%

    No Known Activations