© 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. 1335
    Prev
    Next
    INDEX
    Explanations

    land and ground transport

    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
     seriousness
    -0.25
    å¿«é¤IJ
    -0.24
    åĤ¾
    -0.23
    -containing
    -0.23
    eof
    -0.22
    éĹ¨æ§Ľ
    -0.22
    Äĥm
    -0.22
    åĴĮåıijå±ķ
    -0.21
     isNew
    -0.21
    ôme
    -0.21
    POSITIVE LOGITS
    -ground
    0.28
     transport
    0.28
     land
    0.27
    side
    0.25
     ground
    0.24
    åľ°éĿ¢
    0.24
    plers
    0.24
     terrestrial
    0.23
    交éĢļ
    0.23
     plane
    0.23
    Activations Density 0.039%

    No Known Activations