© 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. 2763
    Prev
    Next
    INDEX
    Explanations

    like to, decided to, let me

    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
    çĶļèĩ³
    -0.36
    çĶļèĩ³è¿ĺ
    -0.34
    actually
    -0.33
     zwar
    -0.31
    ç¡®å®ŀ
    -0.31
     indeed
    -0.30
    èĩ³å°ij
    -0.30
     actually
    -0.29
    åĽºçĦ¶
    -0.28
    å±ħçĦ¶
    -0.28
    POSITIVE LOGITS
    èĢĮå·²
    0.44
     kidding
    0.33
    ç½¢äºĨ
    0.32
    éĤ£ä¹Īç®Ģåįķ
    0.31
     plain
    0.31
    ifiable
    0.30
    æĻ®éĢļçļĦ
    0.30
     thôi
    0.28
    ifi
    0.28
    plain
    0.26
    Activations Density 0.177%

    No Known Activations