© 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. 447
    Prev
    Next
    INDEX
    Explanations

    care of

    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
    å©ł
    -0.21
    åıªè¦ģæľī
    -0.21
    ITS
    -0.21
    mal
    -0.21
    perhaps
    -0.20
    tra
    -0.20
    éĵ¿
    -0.20
    æ¾İæ¹ĥ
    -0.19
    rosse
    -0.19
    å¾Īæ£Ĵ
    -0.19
    POSITIVE LOGITS
    ively
    0.23
    ilian
    0.23
    ingly
    0.22
    itian
    0.22
    eren
    0.22
    ÂŃing
    0.22
    iges
    0.21
    wards
    0.21
    à¸ĩ
    0.20
    oval
    0.20
    Activations Density 0.006%

    No Known Activations