© 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. 14954
    Prev
    Next
    INDEX
    Explanations

    new contributor

    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
    çĶ¸
    -0.19
     Hate
    -0.19
    avo
    -0.19
    (#
    -0.18
    via
    -0.18
    èį¼
    -0.18
    åıĭ们
    -0.18
    èıľ
    -0.18
    Charge
    -0.17
    诰
    -0.17
    POSITIVE LOGITS
    _MS
    0.21
    _Generic
    0.20
    ilon
    0.19
    èĢĮæĿ¥
    0.18
    aroo
    0.18
    åĪļåĪļ
    0.18
    éķ¿çĽ¸
    0.18
    igar
    0.18
    åį³å°Ĩ
    0.18
    oogle
    0.17
    Activations Density 0.005%

    No Known Activations