© 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. 15762
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    AILS
    -0.18
    åĦ¿
    -0.18
    ../../../
    -0.17
    çĤĶ
    -0.16
     Pistol
    -0.16
    亶
    -0.16
    AZY
    -0.16
    gart
    -0.15
    OOSE
    -0.15
    bnb
    -0.15
    POSITIVE LOGITS
    ity
    0.19
    ival
    0.17
    ories
    0.17
    aire
    0.17
     anders
    0.17
    ption
    0.17
    hip
    0.17
    naire
    0.17
    并ä¸į代表
    0.16
    èµ·åĪ°
    0.16
    Activations Density 0.150%

    No Known Activations