© 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. 11797
    Prev
    Next
    INDEX
    Explanations

    Resource disposal and cleanup

    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
    æĦı大
    -0.22
    UNS
    -0.21
    çŃĸ
    -0.20
    alo
    -0.20
     iNdEx
    -0.19
    -center
    -0.19
    ä¸įåĪĨ
    -0.19
    è°Į
    -0.19
    FilterWhere
    -0.19
    ayne
    -0.19
    POSITIVE LOGITS
     Dispose
    0.25
    æ¸ħçIJĨ
    0.25
    éĶĢæ¯ģ
    0.24
     destructor
    0.24
    .dispose
    0.24
    )dealloc
    0.24
    åĽŀæĶ¶
    0.24
    .Dispose
    0.23
    éĩĬæĶ¾
    0.23
     freeing
    0.23
    Activations Density 0.196%

    No Known Activations