© 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. 15501
    Prev
    Next
    INDEX
    Explanations

    violates misuse or claim

    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
    symbol
    -0.22
    apl
    -0.21
     symbol
    -0.21
    utto
    -0.20
    .symbol
    -0.20
    形容
    -0.19
    Symbol
    -0.19
     Ñģимвол
    -0.19
    符åı·
    -0.19
    å®Į
    -0.19
    POSITIVE LOGITS
    éĺ²çĽĹ
    0.23
    æ¶īåıĬ
    0.21
    åħ¬çĽĬ
    0.20
    ROP
    0.19
    æīĵæŀ¶
    0.18
     본
    0.18
    æĹ¥äº§
    0.18
    è¿Ļåıª
    0.18
    ogens
    0.18
    åĪijäºĭæ¡Ī件
    0.18
    Activations Density 0.006%

    No Known Activations