© 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. 13245
    Prev
    Next
    INDEX
    Explanations

    but

    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
     zwar
    -0.21
    uur
    -0.19
    esture
    -0.19
    BUFF
    -0.19
    pmat
    -0.18
    åħĪæĺ¯
    -0.18
    çĹŀ
    -0.18
    çłĴ
    -0.18
    è¦ģä¹Ī
    -0.18
    æŀľçĦ¶
    -0.17
    POSITIVE LOGITS
    æľīä¸ĢçĤ¹
    0.22
    ben
    0.20
    å¾Ħ
    0.18
    æĽ´éĩįè¦ģ
    0.18
    éĻĢ
    0.18
    lers
    0.18
    å°ıç¼ĸ
    0.18
    cher
    0.18
    æģĥ
    0.18
    že
    0.18
    Activations Density 0.067%

    No Known Activations