© 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. 13774
    Prev
    Next
    INDEX
    Explanations

    raining men

    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
    én
    -0.21
    ÑĤÑĥ
    -0.19
    åħ¶
    -0.18
    inea
    -0.17
    .define
    -0.17
    ocity
    -0.17
    ÑĨ
    -0.17
    ä¹ĭåĬĽ
    -0.17
     remark
    -0.17
    æ½ľåĬĽ
    -0.17
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩ
    0.23
    汶
    0.20
     everywhere
    0.20
    对ä»ĸ们
    0.20
    ä»ĸ们éĥ½
    0.19
    gens
    0.19
    еÑĤÑĮ
    0.19
     ambiente
    0.18
    è¿ĻéĩĮçļĦ
    0.18
    åľ¨è¿ĻéĩĮ
    0.18
    Activations Density 0.043%

    No Known Activations