© 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. 2943
    Prev
    Next
    INDEX
    Explanations

    looks like

    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
    äºĨ解åĪ°
    -0.31
    æıŃ示
    -0.25
    æľ¬çĿĢ
    -0.24
    /small
    -0.23
    æĭĬ
    -0.23
    æķħå±ħ
    -0.22
    åīįå¾Ģ
    -0.22
    atte
    -0.22
    æī¾åĩĨ
    -0.22
    èĢĥèĻijåĪ°
    -0.21
    POSITIVE LOGITS
    cape
    0.27
    åĥıæĺ¯
    0.25
     ripe
    0.25
     sovereign
    0.24
    缼åħ¸
    0.24
    ually
    0.24
    Alive
    0.24
    /be
    0.23
     like
    0.23
    iffer
    0.23
    Activations Density 0.036%

    No Known Activations