© 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. 6480
    Prev
    Next
    INDEX
    Explanations

    behind, back, rear

    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
    çݳ
    -0.10
    å¦į
    -0.10
    overn
    -0.10
    æ®ĭçķĻ
    -0.10
    æĽ·
    -0.09
    æ¯Ķè¾ĥå¤ļ
    -0.09
    quam
    -0.09
    箸
    -0.09
    éľ²
    -0.09
    åĬ¬
    -0.09
    POSITIVE LOGITS
    èĥĮåIJİ
    0.17
    èĥĮåIJİçļĦ
    0.14
     behind
    0.14
     Behind
    0.13
    èĥĮæĻ¯
    0.13
    Behind
    0.12
     backing
    0.12
    èĥĮ
    0.12
    身åIJİ
    0.12
    .background
    0.11
    Activations Density 0.087%

    No Known Activations