© 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. 15214
    Prev
    Next
    INDEX
    Explanations

    out, in, up, off, together

    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
    两çĤ¹
    -0.23
    arry
    -0.18
    ÑĢов
    -0.18
    ä¹Łæľīå¾Īå¤ļ
    -0.18
    å½ĵéĢī
    -0.18
    åľ³
    -0.18
    aned
    -0.18
    è¡ĮåĬ¨è®¡åĪĴ
    -0.18
    ivr
    -0.18
    ìľ¡
    -0.17
    POSITIVE LOGITS
    uren
    0.20
    ä¸Ģæł·
    0.19
    äºĨå¤ļå°ij
    0.18
    ä¸ĢåĪĩéĥ½
    0.18
    å·²ä¹ħ
    0.18
    å·²ä¹ħçļĦ
    0.18
    ecessary
    0.17
     dần
    0.17
    çŃ¹
    0.17
    ingly
    0.17
    Activations Density 0.018%

    No Known Activations