© 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. 14821
    Prev
    Next
    INDEX
    Explanations

    interference, docking, implant, antenna

    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
    æĿ³
    -0.21
    çİīçŁ³
    -0.19
    ogra
    -0.19
    efore
    -0.19
     jump
    -0.19
    ç»ıåİĨäºĨ
    -0.18
    ä¸įè§ģ
    -0.18
    ATO
    -0.18
    é¡·
    -0.18
     Mercer
    -0.17
    POSITIVE LOGITS
    å¹²æī°
    0.38
    碰æĴŀ
    0.32
    妨ç¢į
    0.31
     interference
    0.31
    å¹²æ¶ī
    0.27
     interfere
    0.27
    éĺ»ç¢į
    0.27
     interfering
    0.26
    碰
    0.25
    æĹłæĦı
    0.25
    Activations Density 0.139%

    No Known Activations