© 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. 2206
    Prev
    Next
    INDEX
    Explanations

    beta-block

    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
    hunter
    -0.20
    Mounted
    -0.20
    åŁ
    -0.19
    æĪijçĪ¸
    -0.19
    uez
    -0.19
    aire
    -0.19
    /dis
    -0.19
    éĵĨ
    -0.19
    å±Ģéķ¿
    -0.19
    dock
    -0.19
    POSITIVE LOGITS
    ting
    0.26
     somehow
    0.21
    ç»Į
    0.20
    ular
    0.19
    omed
    0.19
    .fhir
    0.19
    ocide
    0.19
     trái
    0.19
     sheer
    0.18
    mas
    0.18
    Activations Density 0.051%

    No Known Activations