© 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. 11536
    Prev
    Next
    INDEX
    Explanations

    before and after comparison

    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
    UIL
    -0.21
    adel
    -0.20
     manh
    -0.20
    eno
    -0.20
    SHIP
    -0.19
    åĴ©
    -0.18
    æĤ±
    -0.18
    åļĨ
    -0.18
    uka
    -0.17
    rette
    -0.17
    POSITIVE LOGITS
    对æ¯Ķ
    0.41
    对çħ§
    0.30
    åıĺåĮĸ
    0.24
     comparison
    0.23
    ä¸¤å¼ł
    0.23
    å·®è·Ŀ
    0.23
    comparison
    0.22
     contrast
    0.22
    çħ§çīĩ
    0.22
    ÙĤار
    0.21
    Activations Density 0.047%

    No Known Activations