© 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. 1834
    Prev
    Next
    INDEX
    Explanations

    comparison or similarity

    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
    inct
    -0.26
    åĻªéŁ³
    -0.24
    è§Ĵ度çľĭ
    -0.23
    æ¶Ī
    -0.22
    æ®ĩ
    -0.22
    äºĴéĢļ
    -0.22
    ä¸įä»ħèĥ½
    -0.22
    ä»Ģ
    -0.21
    ä»ķ
    -0.21
    :result
    -0.21
    POSITIVE LOGITS
     others
    0.33
     other
    0.33
    å½ĵå¹´
    0.30
    åħ¶å®ĥ
    0.30
    åħ¶ä»ĸçļĦ
    0.30
    å½ĵåĪĿ
    0.29
    åħ¶ä»ĸ
    0.29
    åħ¶ä»ĸ人
    0.26
     earlier
    0.26
     previously
    0.26
    Activations Density 0.029%

    No Known Activations