© 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. 788
    Prev
    Next
    INDEX
    Explanations

    motorcycle enthusiasts and clubs

    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
    ness
    -0.30
    NESS
    -0.22
    lands
    -0.22
    å¯ĦãģĽ
    -0.21
    ä¼ĺè´¨çļĦ
    -0.20
    -paying
    -0.20
    inger
    -0.20
    rella
    -0.19
    coat
    -0.19
    locked
    -0.19
    POSITIVE LOGITS
    /table
    0.24
     enthusiasts
    0.24
    驾驶è¯ģ
    0.22
     enthusiast
    0.21
    /mobile
    0.21
    驾çħ§
    0.21
    hair
    0.20
    ðŁĴ¨
    0.20
    çĪ±å¥½èĢħ
    0.20
    alley
    0.20
    Activations Density 0.007%

    No Known Activations