© 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. 11299
    Prev
    Next
    INDEX
    Explanations

    poll

    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
    eam
    -0.23
    earch
    -0.20
    ä¸ĢåĽŀäºĭ
    -0.19
    upert
    -0.19
    就好åĥı
    -0.17
    uales
    -0.17
    ially
    -0.17
    ibold
    -0.17
    åĽŀäºĭ
    -0.16
    à¹Ħà¸ģล
    -0.16
    POSITIVE LOGITS
    ingly
    0.23
    ers
    0.22
    ings
    0.21
    ×ķת
    0.21
    itory
    0.20
    ìį¨
    0.19
    ë§ģ
    0.18
    smith
    0.18
    inator
    0.18
    ination
    0.17
    Activations Density 0.008%

    No Known Activations