© 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. 12250
    Prev
    Next
    INDEX
    Explanations

    erosion and corrosion

    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
    ä¸Ģåľº
    -0.19
    åĴĮåľ°åĮº
    -0.19
    áticas
    -0.17
    tons
    -0.17
    WithValue
    -0.17
    loud
    -0.17
    sWith
    -0.17
    جار
    -0.16
    оÑģоб
    -0.16
    latex
    -0.16
    POSITIVE LOGITS
    æ®Ĩ
    0.21
    æİīäºĨ
    0.20
    壮大
    0.18
    æİī
    0.18
    /stretch
    0.18
    ä¸įåłª
    0.18
    ently
    0.17
    éĤĻ
    0.17
    DED
    0.17
    åIJİçļĦ
    0.17
    Activations Density 0.012%

    No Known Activations