© 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. 1469
    Prev
    Next
    INDEX
    Explanations

    shipping costs or thresholds

    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
     Assertion
    -0.27
    äº¤æĽ¿
    -0.26
    Assertion
    -0.25
    严èĤĥ
    -0.24
    åĽ´è§Ĥ
    -0.24
    åĪĽéĢłæĢ§
    -0.24
    scape
    -0.24
     altern
    -0.23
     briefed
    -0.23
    åļ¼
    -0.23
    POSITIVE LOGITS
    éĢģè´§
    0.37
    åıijè´§
    0.34
     freight
    0.32
    æīĺè¿IJ
    0.30
    éħįéĢģ
    0.30
    è¿IJè´¹
    0.30
    è´§çī©
    0.29
    æĢ»ä»·
    0.29
     shipment
    0.28
     shipping
    0.28
    Activations Density 0.015%

    No Known Activations