© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2934
    Prev
    Next
    INDEX
    Explanations

    #include <stdio.h>

    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
    å®Ī
    -0.23
    ä¸į失
    -0.23
    éķ¿éĢĶ
    -0.21
    strip
    -0.21
    -selector
    -0.21
    aste
    -0.21
    ington
    -0.21
    ÑĪÑĥ
    -0.21
    çķĶ
    -0.21
     analogy
    -0.20
    POSITIVE LOGITS
    labs
    0.24
     Suspension
    0.24
    edBy
    0.23
    ä¼ĹçŃ¹
    0.22
    Susp
    0.22
     suspension
    0.22
    ủ
    0.21
    éĶŃ
    0.21
    æĿ¿åĿĹ
    0.20
    Ĥ¬
    0.20
    Activations Density 0.046%

    No Known Activations