© 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. 12777
    Prev
    Next
    INDEX
    Explanations

    legal rights and procedures

    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
    çĦ¦
    -0.22
    èĩªå®¶
    -0.21
    å¹´è½»çļĦ
    -0.21
     selfish
    -0.20
    èĩªç§ģ
    -0.20
    åĬ¿å¤´
    -0.20
    Anth
    -0.20
    _REL
    -0.19
    æŀ¢çº½
    -0.19
    Pure
    -0.19
    POSITIVE LOGITS
     rights
    0.25
    kers
    0.21
    rights
    0.20
    åħ¨æµģç¨ĭ
    0.20
     hearing
    0.20
    LOTS
    0.20
     guarding
    0.20
    orra
    0.20
    CEF
    0.19
     Chambers
    0.19
    Activations Density 0.020%

    No Known Activations