© 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. 2445
    Prev
    Next
    INDEX
    Explanations

    powered cat

    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
    elves
    -0.26
     Heard
    -0.25
    .mozilla
    -0.25
    .Assembly
    -0.24
     Flip
    -0.24
    ä¿£
    -0.24
    schlü
    -0.23
    _EXTENSION
    -0.23
    å½ĵæĪij们
    -0.23
    velopment
    -0.22
    POSITIVE LOGITS
     said
    0.27
    说éģĵ
    0.27
    楼主
    0.26
     gonna
    0.25
    banana
    0.25
    boy
    0.25
    andi
    0.23
    æ²³æµģ
    0.23
     failing
    0.23
     dut
    0.23
    Activations Density 0.133%

    No Known Activations