© 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. 108
    Prev
    Next
    INDEX
    Explanations

    necessary expense, requirement, and steps

    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
    smith
    -0.23
    оваÑı
    -0.20
    овÑĭй
    -0.20
    ï¸
    -0.20
    sWith
    -0.20
    çĿ¨
    -0.19
     nominal
    -0.19
    ney
    -0.19
     preferring
    -0.18
    -CN
    -0.18
    POSITIVE LOGITS
    èĩ¾
    0.32
    mente
    0.26
     evils
    0.25
    hood
    0.23
     evil
    0.23
    ALLY
    0.22
    ment
    0.22
    ly
    0.22
    lessly
    0.21
     precautions
    0.21
    Activations Density 0.018%

    No Known Activations