© 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. 14654
    Prev
    Next
    INDEX
    Explanations

    radio and television shows

    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
    äºĨåĩºæĿ¥
    -0.20
     executions
    -0.20
    åģľå·¥
    -0.18
    èĪĶ
    -0.18
     cheapest
    -0.18
    çį¬
    -0.18
    execution
    -0.17
    LAN
    -0.17
    æµĩ
    -0.17
    avi
    -0.17
    POSITIVE LOGITS
    hower
    0.20
    ä»ĬæĻļ
    0.20
    .host
    0.19
    å±ĬæŶ
    0.19
    :param
    0.19
     chÆ°Æ¡ng
    0.19
    éķ¿éķ¿
    0.18
    èģļçĦ¦
    0.18
    onor
    0.18
    è®®
    0.18
    Activations Density 0.020%

    No Known Activations