© 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. 14803
    Prev
    Next
    INDEX
    Explanations

    retaliation or backlash

    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
    è¾ĩ
    -0.20
    eters
    -0.19
    çĭ¬è§Ĵåħ½
    -0.19
    æĹħé¦Ĩ
    -0.18
    igm
    -0.18
    å®ļäºĨ
    -0.17
    /functions
    -0.17
    é¢Ĩ
    -0.17
    è¸ıå®ŀ
    -0.17
    stor
    -0.17
    POSITIVE LOGITS
    æݪæĸ½
    0.24
     against
    0.19
    against
    0.19
    éĢĨ
    0.18
    æ®ĥ
    0.18
    踢
    0.17
    èĽ¾
    0.17
     Against
    0.17
    èĴ¯
    0.17
    lick
    0.17
    Activations Density 0.007%

    No Known Activations