© 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. 13125
    Prev
    Next
    INDEX
    Explanations

    ratings or rankings

    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
    HONE
    -0.23
    èĪįå¾Ĺ
    -0.20
    奢
    -0.19
    ened
    -0.18
    otta
    -0.18
    _BE
    -0.17
    _LOGGER
    -0.17
    ofile
    -0.17
    æ®ī
    -0.17
    (ix
    -0.17
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.28
    åıĮè¾¹
    0.22
    é¢ĨåħĪåľ°ä½į
    0.20
    æIJŃè½½
    0.18
    线ä¸ĭ
    0.17
    andro
    0.17
    éĩįè¦ģæĦıä¹ī
    0.16
    bindParam
    0.16
    è§ģè¯ģäºĨ
    0.16
    ä¹ĭ乡
    0.16
    Activations Density 0.007%

    No Known Activations