© 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. 11967
    Prev
    Next
    INDEX
    Explanations

    real estate for sale

    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
    嵯
    -0.19
    meric
    -0.18
     ê°IJ
    -0.17
    ëł¥
    -0.17
    acker
    -0.17
    _oc
    -0.17
     ìĹŃ
    -0.17
    amer
    -0.17
    æ¯ıå¹´éĥ½
    -0.17
    è´¨éĩıåĴĮ
    -0.16
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.17
    ARS
    0.16
     Barnes
    0.16
    ä¸ĸçķĮè§Ĥ
    0.16
    çĤ¹å¤´
    0.16
    åĨħå¿ĥçļĦ
    0.16
    -meta
    0.15
    MITTED
    0.15
    ä¹ĭå¤Ħ
    0.15
     sÅĤow
    0.15
    Activations Density 0.007%

    No Known Activations