© 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. 15916
    Prev
    Next
    INDEX
    Explanations

    portable [device type]

    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
    /her
    -0.25
    /or
    -0.23
    -0.19
    åħ¥ãĤĬ
    -0.19
    ãģĹãģ¾ãģĦ
    -0.18
    ery
    -0.18
     ÐĶмиÑĤÑĢ
    -0.17
    nect
    -0.17
    elp
    -0.17
     ÐŁÐ¾Ñĩем
    -0.16
    POSITIVE LOGITS
    ebb
    0.19
     дÑĥÑħ
    0.18
    ÑıÑĤÑĮ
    0.17
    注æĺİåĩºå¤Ħ
    0.17
    ee
    0.16
    æĢ§åĴĮ
    0.16
    æĢ§å¼º
    0.16
    esto
    0.15
     جدا
    0.15
    -ish
    0.15
    Activations Density 0.006%

    No Known Activations