© 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. 16157
    Prev
    Next
    INDEX
    Explanations

    heart attack

    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
    åĪ»èĭ¦
    -0.19
    èĨ³
    -0.18
    ->__
    -0.18
    illian
    -0.18
    åĮĸè¿Ľç¨ĭ
    -0.18
    æĺĻ
    -0.17
    .mainloop
    -0.17
    èĢ³è¾¹
    -0.17
    uments
    -0.17
    dale
    -0.17
    POSITIVE LOGITS
    次æķ°
    0.21
    åīįå¤ķ
    0.20
    éĥ¨åĪĨåĨħ容
    0.19
    åīį
    0.19
    身亡
    0.18
    Occurred
    0.18
    -like
    0.18
    FU
    0.17
    åīįåĩłå¤©
    0.17
    åīįçŀ»
    0.17
    Activations Density 0.020%

    No Known Activations