© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1214
    Prev
    Next
    INDEX
    Explanations

    indentations, recess, notch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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¸Ĭæľī
    -0.27
    ä¸ĬçļĦ
    -0.25
    ä¸Ĭãģ®
    -0.25
     vinc
    -0.23
    ç¹
    -0.23
    绳
    -0.23
     throughput
    -0.22
    ä¸Ĭãģ§
    -0.22
     Attached
    -0.21
    å¨ĺ
    -0.21
    POSITIVE LOGITS
    åĩ¹
    0.36
    å¾Īæ·±
    0.36
     therein
    0.28
     recess
    0.27
     depths
    0.27
    éĻ·
    0.27
    æ·±å¤Ħ
    0.26
    å£ij
    0.26
    æ´¼
    0.25
    æĽ´æ·±
    0.25
    Activations Density 0.071%

    No Known Activations