© 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. 10997
    Prev
    Next
    INDEX
    Explanations

    problems, errors, beauty, amazing

    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¸IJ
    -0.22
    orent
    -0.18
    velt
    -0.18
    amic
    -0.18
    _pv
    -0.18
    å´§
    -0.18
    anni
    -0.18
    ặng
    -0.17
    sov
    -0.17
    ä¼łç»Łäº§ä¸ļ
    -0.17
    POSITIVE LOGITS
    åĺĽ
    0.26
    dba
    0.19
     Dimensions
    0.19
    çĶļèĩ³
    0.19
     incluso
    0.19
    太å¤ļäºĨ
    0.19
     even
    0.18
     enim
    0.18
     Curriculum
    0.18
    _('
    0.18
    Activations Density 0.273%

    No Known Activations