© 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. 11116
    Prev
    Next
    INDEX
    Explanations

    Hague, Hag, AG, atham

    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
    s
    -0.19
    æĺĶ
    -0.18
    scape
    -0.18
    baugh
    -0.17
    же
    -0.17
    ä¸įäºĨ
    -0.17
    sheets
    -0.16
    ëıĦ
    -0.15
     Bald
    -0.15
    å¨ĥå¨ĥ
    -0.15
    POSITIVE LOGITS
    cus
    0.19
    itude
    0.17
    ging
    0.17
    ectors
    0.17
    onus
    0.17
    رة
    0.16
    ewise
    0.16
    king
    0.15
    ACHE
    0.15
    .Types
    0.15
    Activations Density 0.015%

    No Known Activations