© 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. 1406
    Prev
    Next
    INDEX
    Explanations

    vehicle body parts and types

    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
    hani
    -0.28
    _threads
    -0.25
    zung
    -0.25
    Nib
    -0.24
    -thread
    -0.24
    大åĶIJ
    -0.24
    åĸĿèĮ¶
    -0.23
    _THREADS
    -0.23
    éĨĴäºĨ
    -0.23
    -scripts
    -0.23
    POSITIVE LOGITS
     luggage
    0.27
     Garage
    0.26
    åĬ¡å®ŀ
    0.25
     Polo
    0.24
     storage
    0.24
    åĤ¨
    0.24
    æĭĸ
    0.24
    ä»ĵåĤ¨
    0.24
    车åŀĭ
    0.24
    货车
    0.24
    Activations Density 0.007%

    No Known Activations