© 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. 15177
    Prev
    Next
    INDEX
    Explanations

    places name

    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
     X
    -0.20
    -0.20
    i
    -0.19
     end
    -0.19
     D
    -0.19
     t
    -0.19
    .OnClickListener
    -0.18
    ä¼ļä¸Ĭ
    -0.18
     R
    -0.18
    y
    -0.18
    POSITIVE LOGITS
    ени
    0.20
    å¾Īå¤ļæľĭåıĭ
    0.19
    çĦ¦èĻij
    0.19
    æĢħ
    0.18
    æįį
    0.18
     пÑĢеп
    0.18
    antor
    0.18
    ington
    0.17
    culate
    0.17
    äºĨ解ä¸Ģä¸ĭ
    0.17
    Activations Density 0.711%

    No Known Activations