© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 60
    Prev
    Next
    INDEX
    Explanations

    equality and diversity

    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
    éĩįç£ħ
    -0.27
     timed
    -0.26
     preview
    -0.26
    æ·»åĬł
    -0.26
     trailing
    -0.26
     postseason
    -0.25
    ä¸ļåĨħ人士
    -0.25
     underestimated
    -0.25
    ardown
    -0.25
    è§ģè¯ģäºĨ
    -0.25
    POSITIVE LOGITS
    èĩªçĶ±
    0.36
     freedoms
    0.36
    约æĿŁ
    0.35
     Ñģвобод
    0.34
    å°Ĭéĩį
    0.34
     sovereignty
    0.34
    个ä½ĵ
    0.32
    èĩªæ²»
    0.32
    çĶŁæ´»çݯå¢ĥ
    0.32
    çĶŁäº§åĬĽ
    0.32
    Activations Density 0.056%

    No Known Activations