© 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. 2754
    Prev
    Next
    INDEX
    Explanations

    comic book heroes and villains

    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
    æ´Ħ
    -0.24
     COPYING
    -0.24
    æIJ¬å®¶
    -0.22
     Associate
    -0.22
    è¿ģ移
    -0.22
     Transfer
    -0.21
    erer
    -0.21
    åįĩ温
    -0.21
     apl
    -0.21
     bump
    -0.21
    POSITIVE LOGITS
    Crime
    0.33
    _pulse
    0.31
    èĦī
    0.28
    pulse
    0.28
     Crime
    0.28
     nightly
    0.28
    æ¸ħæī«
    0.27
     crime
    0.26
     Lexington
    0.26
    åħ¨å¤©
    0.26
    Activations Density 0.018%

    No Known Activations