© 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. 2549
    Prev
    Next
    INDEX
    Explanations

    phrases or words

    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
     Tried
    -0.24
    _iso
    -0.23
    éģįå¸ĥ
    -0.23
     Nó
    -0.22
    ",-
    -0.22
    Hung
    -0.22
     haci
    -0.21
    abis
    -0.21
    sis
    -0.21
     Abyss
    -0.21
    POSITIVE LOGITS
     consisting
    0.27
    -val
    0.27
    æIJŃ
    0.25
    èĪ«
    0.24
     formed
    0.24
     phrases
    0.23
     CID
    0.23
     enclosed
    0.22
    ç§ĺ书
    0.22
    太åŃIJ
    0.22
    Activations Density 0.058%

    No Known Activations