© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1182
    Prev
    Next
    INDEX
    Explanations

    surgery

    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
    ovo
    -0.23
    ../
    -0.23
    ness
    -0.21
    UMENT
    -0.21
    ../../../
    -0.20
    ple
    -0.20
    izard
    -0.20
    NESS
    -0.19
    zelf
    -0.19
    å¤ĸçķĮ
    -0.18
    POSITIVE LOGITS
    urally
    0.26
    åIJİçļĦ
    0.24
    身亡
    0.21
    yard
    0.21
    åľºä¸Ĭ
    0.21
    ically
    0.20
    -ready
    0.20
    -induced
    0.20
    -related
    0.20
    éĹ¨æ§Ľ
    0.19
    Activations Density 0.054%

    No Known Activations