© 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. 13264
    Prev
    Next
    INDEX
    Explanations

    self-references and experiences

    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
     fred
    -0.19
    åģļä¸Ģ个
    -0.19
    æĤ
    -0.19
    声åĵį
    -0.18
    _datas
    -0.18
    ored
    -0.18
    让èĩªå·±
    -0.18
    оÑĢо
    -0.17
    æĵįåľº
    -0.17
    éĺĻ
    -0.17
    POSITIVE LOGITS
    以åīį
    0.20
    ITION
    0.20
     обо
    0.19
    å¸Ĥä¸Ńå¿ĥ
    0.19
    çĻ¾ç§ij
    0.18
    èĨĿ
    0.18
    åĬ¨åijĺ
    0.18
    棱
    0.18
    ç«ŀäºī
    0.18
    çļĦå®ŀéĻħ
    0.18
    Activations Density 0.155%

    No Known Activations