© 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. 10727
    Prev
    Next
    INDEX
    Explanations

    helping [group/entity]

    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
    pta
    -0.19
    /apis
    -0.18
    igers
    -0.17
    ä¸įçķĻ
    -0.17
    éĩĩåıĸ
    -0.17
    éĽķ
    -0.17
    æĪijä¸įæĺ¯
    -0.17
    åĬŀ
    -0.17
    åıijå±ķ空éĹ´
    -0.17
    æŶéĹ´åĴĮ
    -0.16
    POSITIVE LOGITS
    人éĥ½
    0.26
     to
    0.23
     laure
    0.18
    以èī²
    0.18
    ãĥ¼
    0.18
    å¤Ķ
    0.17
    éĥ½èĥ½å¤Ł
    0.17
    (lambda
    0.17
    icide
    0.17
    lh
    0.17
    Activations Density 0.012%

    No Known Activations