© 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. 15601
    Prev
    Next
    INDEX
    Explanations

    hitting and striking

    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
    éĻħ
    -0.22
    .flow
    -0.22
    é¢Ģ
    -0.20
    ç¼ķ
    -0.20
    å½ķ
    -0.20
    æĹłéĻIJ
    -0.20
    åįĪåIJİ
    -0.20
    ä¹ĭåĨħ
    -0.19
     ambit
    -0.18
    inar
    -0.18
    POSITIVE LOGITS
    æķ²
    0.40
    éĶ¤
    0.33
    糸
    0.32
    åĩ»
    0.32
    æĴŀ
    0.29
    æĵĬ
    0.29
     hammer
    0.26
    æį¶
    0.26
     knocking
    0.24
    碰æĴŀ
    0.24
    Activations Density 0.041%

    No Known Activations