© 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. 10974
    Prev
    Next
    INDEX
    Explanations

    like the other

    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
    ä¸įä»ħ
    -0.23
    ç«ŁçĦ¶
    -0.22
    åĵªæĢķæĺ¯
    -0.21
    åĵªæĢķ
    -0.21
    éĻ¤äºĨ
    -0.20
    ADI
    -0.20
    ä¸įä½Ĩ
    -0.20
    åį³ä½¿
    -0.19
    æľŁ
    -0.19
    comb
    -0.19
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.27
    åħ¶å®ĥ
    0.27
    åħ¶ä»ĸ
    0.27
    å¾Ģå¹´
    0.26
    ä¹ĭåīįçļĦ
    0.25
     other
    0.25
     otros
    0.25
    以å¾Ģ
    0.25
    åħ¶å®ĥéĹ®é¢ĺ
    0.24
    大å¤ļæķ°
    0.24
    Activations Density 0.031%

    No Known Activations