© 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. 14473
    Prev
    Next
    INDEX
    Explanations

    cardholder information, xerox copies, convenience checks

    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
     khảo
    -0.21
     Rift
    -0.20
    iev
    -0.19
     Hust
    -0.19
    igin
    -0.19
    åĽłåľ°åĪ¶å®ľ
    -0.19
    itore
    -0.19
    creens
    -0.19
    _hd
    -0.18
    RH
    -0.18
    POSITIVE LOGITS
    åį¡çīĩ
    0.26
    åı·çłģ
    0.25
    ä¿¡çĶ¨åį¡
    0.25
    åķĨä¸ļéĵ¶è¡Į
    0.23
    å¤įåį°
    0.23
    线ä¸ĭ
    0.23
    滥
    0.23
    å¤įåį°ä»¶
    0.22
     card
    0.21
    éĵ¶è¡Įåį¡
    0.21
    Activations Density 0.023%

    No Known Activations