© 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. 11694
    Prev
    Next
    INDEX
    Explanations

    valley, tunnel, alley, harbor

    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¸ĬçļĦ
    -0.23
     behalf
    -0.21
    æ¢Ĺ
    -0.20
    æ·¼
    -0.19
    ä¸Ĭæľī
    -0.19
    å°ıå§IJ
    -0.19
    è¯Ī
    -0.19
     Marcus
    -0.19
    ä¸Ĭåİ»
    -0.18
    çĸµ
    -0.18
    POSITIVE LOGITS
    åħ¥åı£
    0.25
    çĭŃ
    0.25
    åĨħ
    0.25
    å¾Īæ·±
    0.24
    åı£
    0.24
    çª
    0.24
    æ·±å¤Ħ
    0.24
     cavity
    0.23
    åĨħçļĦ
    0.23
    ãģ«åħ¥
    0.23
    Activations Density 0.230%

    No Known Activations