© 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. 11681
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation

    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
    åĢĴæĺ¯
    -0.23
    ExecutionContext
    -0.21
    åħ·ä½ĵæĥħåĨµ
    -0.20
    è£Ķ
    -0.20
    åİ»äºĨ
    -0.19
    æĽ´åĥıæĺ¯
    -0.19
    remainder
    -0.19
    åīŁ
    -0.19
    åı«
    -0.18
    åıįæŃ£
    -0.18
    POSITIVE LOGITS
    éļ¾åħį
    0.26
    åĽłæѤ
    0.25
    æĪij们éľĢè¦ģ
    0.24
    åĽłèĢĮ
    0.24
    å¾Īå¤ļæŶåĢĻ
    0.23
    æ³ħ
    0.23
     поÑįÑĤомÑĥ
    0.23
    éľĢè¦ģçĶ¨
    0.22
    æīĢ以æĪij们
    0.22
    æĪij们çļĦ
    0.21
    Activations Density 0.497%

    No Known Activations