© 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. 2580
    Prev
    Next
    INDEX
    Explanations

    findings and results

    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
     machinery
    -0.26
     tomorrow
    -0.26
    æĬĬå®ĥ
    -0.24
    zo
    -0.24
     pose
    -0.23
    éĹ®ä»ĸ
    -0.23
    çĩİ
    -0.22
     voice
    -0.22
    åĬŀ好
    -0.22
    èķĻ
    -0.22
    POSITIVE LOGITS
    ç»ĵæŀľæĺ¾ç¤º
    0.50
    ç»ĵæŀľ
    0.46
     results
    0.42
    çļĦç»ĵæŀľ
    0.41
    ç»ĵ论
    0.40
     conclusions
    0.40
     findings
    0.40
     resultados
    0.39
    results
    0.38
    çµIJæŀľ
    0.37
    Activations Density 0.200%

    No Known Activations