© 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. 14713
    Prev
    Next
    INDEX
    Explanations

    prohibition, alcohol, morality

    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
    åľ°è´¨
    -0.23
    chron
    -0.21
    VIP
    -0.21
    éĴ¤
    -0.20
     chron
    -0.20
     Rohingya
    -0.20
    éĶ°
    -0.19
    å½ķ
    -0.19
    bé
    -0.19
    çķª
    -0.18
    POSITIVE LOGITS
    éħĴ
    0.26
    严ç¦ģ
    0.25
    æĮ¡ä½ı
    0.23
    ç¦ģæŃ¢
    0.23
     Alcohol
    0.21
     alcohol
    0.20
    严åİī
    0.20
    osal
    0.20
     crus
    0.19
     wine
    0.19
    Activations Density 0.026%

    No Known Activations