© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10577
    Prev
    Next
    INDEX
    Explanations

    forced or unwanted actions

    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
    Negative Logits
     Tin
    -0.21
    è¦ģç´§
    -0.20
     Dove
    -0.20
     ÐĵÑĢ
    -0.20
     Immigration
    -0.20
    è°ħ
    -0.19
     Attr
    -0.19
    ä¸įåĩºæĿ¥
    -0.19
    GRE
    -0.18
    平常
    -0.18
    POSITIVE LOGITS
    强åĪ¶
    0.45
    被迫
    0.40
    强迫
    0.40
     forced
    0.37
     Forced
    0.34
     compulsory
    0.33
    forced
    0.32
     unwanted
    0.31
     forcing
    0.30
     mandatory
    0.30
    Activations Density 0.165%

    No Known Activations