© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12607
    Prev
    Next
    INDEX
    Explanations

    missile or torpedo

    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
    iben
    -0.21
    éĬ®
    -0.19
    EMON
    -0.19
    ings
    -0.19
    饮éħĴ
    -0.19
    èĩªåĪ¶
    -0.18
    åŁºè°ĥ
    -0.18
    éĵ¨
    -0.18
    scr
    -0.18
    odo
    -0.17
    POSITIVE LOGITS
    å¤Ń
    0.22
    بار
    0.21
    åºĵéĩĮ
    0.20
    è¿ľæĸ¹
    0.20
    è¹Ĭ
    0.20
    åĤį
    0.19
     arrow
    0.19
    ä¸Ģè½®
    0.18
    åħĪè¿ĽæĬĢæľ¯
    0.18
    ä¸Ģ对ä¸Ģ
    0.18
    Activations Density 0.010%

    No Known Activations