© 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. 14631
    Prev
    Next
    INDEX
    Explanations

    Vladimir or Dracula-related names

    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
    bare
    -0.19
    reuse
    -0.18
    agnostic
    -0.18
    _reporting
    -0.18
    åĮħ袱
    -0.18
    inge
    -0.17
    shal
    -0.17
    å¤©åĽ½
    -0.17
    ãģĦãģĨ
    -0.17
    erializer
    -0.17
    POSITIVE LOGITS
    raz
    0.20
    ç»ħ
    0.20
    åĴĮä»ĸçļĦ
    0.20
    èĿĻ
    0.19
    第ä¸Ģéĥ¨
    0.19
    äºĨä»ĸçļĦ
    0.19
    å¥¥åľ°åĪ©
    0.19
     Ladies
    0.18
    rd
    0.18
    ä¼Łå¤§çļĦ
    0.18
    Activations Density 0.007%

    No Known Activations