© 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. 12190
    Prev
    Next
    INDEX
    Explanations

    genesis, evolution, findings

    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
    çī¹æľĹ
    -0.21
    ignon
    -0.20
    禳
    -0.20
    avaÅŁ
    -0.20
    èŀ«
    -0.20
    ango
    -0.19
    LEASE
    -0.19
    AVA
    -0.19
    éķ¿å¤§
    -0.19
     pled
    -0.19
    POSITIVE LOGITS
    åŃķèĤ²
    0.29
     humanoid
    0.28
    èĢĥåı¤
    0.28
    人ä½ĵ
    0.24
    ev
    0.23
    DNA
    0.23
    èĥļ
    0.22
     genesis
    0.22
    ankind
    0.22
    çĶŁåij½
    0.22
    Activations Density 0.065%

    No Known Activations