© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15031
    Prev
    Next
    INDEX
    Explanations

    recommendation or evaluation

    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
    gee
    -0.20
    åģļä¸Ģ个
    -0.19
    RELATED
    -0.18
    ä¸įæĩĤ
    -0.18
     Lucky
    -0.18
     Maher
    -0.18
     ode
    -0.18
    æ²ĵ
    -0.17
    uess
    -0.17
    æıIJ示
    -0.17
    POSITIVE LOGITS
    ä¸Ģçľĭ
    0.23
    -worthy
    0.22
    åģ¿
    0.21
    åı¯æĥ³
    0.21
     Fil
    0.20
    åĢ¾
    0.20
     worth
    0.20
    称
    0.20
    åħ´è¶£
    0.20
    åłªç§°
    0.19
    Activations Density 0.070%

    No Known Activations