© 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. 705
    Prev
    Next
    INDEX
    Explanations

    conductive lines and layers

    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
     tires
    -0.25
     durations
    -0.24
    æł¼å¼ı
    -0.24
     оÑĢигинал
    -0.23
     unfold
    -0.23
    è¾Ī
    -0.23
     Wind
    -0.23
     Duration
    -0.22
    _DROP
    -0.22
    çļĦè¿ĩç¨ĭ
    -0.22
    POSITIVE LOGITS
    çķħéĢļ
    0.35
     metal
    0.31
     metals
    0.31
     solder
    0.30
    éĢļçķħ
    0.29
    -metal
    0.28
    缸éĢļ
    0.28
     electrode
    0.28
     conductivity
    0.27
    导
    0.27
    Activations Density 0.148%

    No Known Activations