© 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. 12706
    Prev
    Next
    INDEX
    Explanations

    attending events, meetings, or church regularly

    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
    ä¸Ģ代
    -0.25
    åħ¶å®ĥéĹ®é¢ĺ
    -0.22
    å¤Ń
    -0.20
    æĪĺåľºä¸Ĭ
    -0.20
    æĶ¶åĪ°äºĨ
    -0.20
    ä¸Ģçŀ¬éĹ´
    -0.20
    _PATCH
    -0.19
    wort
    -0.19
     nhuáºŃn
    -0.18
    顽
    -0.18
    POSITIVE LOGITS
    åľºæīĢ
    0.26
    社ä¼ļç»Ħç»ĩ
    0.21
    社ä¼ļ
    0.20
    é£İæ°Ķ
    0.20
    社
    0.20
    HDR
    0.19
    两次
    0.19
     halls
    0.19
    offline
    0.19
    APA
    0.19
    Activations Density 0.049%

    No Known Activations