© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11396
    Prev
    Next
    INDEX
    Explanations

    suicide bomber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    åħĥå®Ŀ
    -0.26
    æĺİçıł
    -0.20
    ä¸ĭè°ĥ
    -0.20
    ä¸Ŀä¸Ŀ
    -0.20
    Privacy
    -0.20
    alias
    -0.20
    å¾®å¦Ļ
    -0.20
    æ¸ħæ·¡
    -0.19
    å¿ĥæĥ³
    -0.18
    è°ĥçIJĨ
    -0.18
    POSITIVE LOGITS
     mask
    0.23
    bote
    0.22
    -mask
    0.22
     Redistributions
    0.20
     ranks
    0.20
     suicide
    0.20
    ideon
    0.20
    iran
    0.19
     ram
    0.19
    icial
    0.19
    Activations Density 0.007%

    No Known Activations