© 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. 31
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    crud
    -0.26
    allee
    -0.25
    è¦ĨçĽĸçİĩ
    -0.25
     гаÑĢ
    -0.24
    è´²
    -0.23
    åĩºåľŁ
    -0.23
    }}},↵
    -0.23
    _coll
    -0.23
    asca
    -0.23
    Extent
    -0.22
    POSITIVE LOGITS
    çľĭ好
    0.25
    æĽ¿
    0.24
     puzzle
    0.24
    åı·
    0.23
     til
    0.23
    Kel
    0.23
    cn
    0.23
    ead
    0.22
    访éĹ®
    0.22
     spaces
    0.22
    Activations Density 0.020%

    No Known Activations