© 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. 12170
    Prev
    Next
    INDEX
    Explanations

    sexual relations and consent

    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
    èł¹
    -0.21
    ateway
    -0.20
    åįķ身
    -0.20
    缺çĤ¹
    -0.20
    绣
    -0.20
    odian
    -0.19
    çĤĬ
    -0.19
    ibles
    -0.19
    éĹ°
    -0.19
    æĤłéĹ²
    -0.18
    POSITIVE LOGITS
     consent
    0.24
    éĺ²åį«
    0.21
    导读
    0.21
     tokenize
    0.20
     barr
    0.20
     recip
    0.19
    義åĭĻ
    0.19
     bystand
    0.19
    ymb
    0.19
    Partner
    0.19
    Activations Density 0.030%

    No Known Activations