© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12105
    Prev
    Next
    INDEX
    Explanations

    mac products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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«Ĥ
    -0.22
    aphore
    -0.21
    å°±å¤Ł
    -0.21
    女åŃ©åŃIJ
    -0.20
    æĪĴ
    -0.19
    krit
    -0.19
    wealth
    -0.19
    累累
    -0.19
    åĦ¿
    -0.19
    -align
    -0.19
    POSITIVE LOGITS
    失
    0.21
    çĪ¶åŃIJ
    0.19
     Gri
    0.19
     layers
    0.19
    ernals
    0.18
     Packing
    0.18
    æĤŃ
    0.18
     ayr
    0.18
    éĻ£
    0.17
    æĥ¯
    0.17
    Activations Density 0.004%

    No Known Activations