© 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. 15164
    Prev
    Next
    INDEX
    Explanations

    removal or loosening

    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
     Mon
    -0.21
     Hoch
    -0.20
    ustom
    -0.20
     ver
    -0.20
     vir
    -0.20
    Ops
    -0.20
    ä¸Ģ天
    -0.20
    ane
    -0.20
    åĸ§
    -0.20
    upo
    -0.19
    POSITIVE LOGITS
    æĭĨéĻ¤
    0.23
    ICLE
    0.22
    _OW
    0.22
    æķĻèĤ²åŁ¹è®Ń
    0.21
    _RAM
    0.21
    è·Łè¿Ľ
    0.21
    解éĻ¤
    0.20
    éħįåIJĪ
    0.20
     Extraction
    0.20
    æī¾åĩĨ
    0.20
    Activations Density 0.057%

    No Known Activations