© 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. 12071
    Prev
    Next
    INDEX
    Explanations

    BBC, Mr, captions, GMT, Indian guide

    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
    åĽłåŃIJ
    -0.22
    磶
    -0.21
    迳
    -0.21
     Lima
    -0.19
    minimum
    -0.19
    returnValue
    -0.19
    ãĥĹãĥ¬ãĤ¤
    -0.19
    æ±´
    -0.18
    ä¸ĭä¸Ģ个
    -0.18
    ä¿Ĺ
    -0.18
    POSITIVE LOGITS
     BBC
    0.26
    BBC
    0.25
    rô
    0.21
    讲课
    0.20
    bbc
    0.19
    èķĪ
    0.19
    vê
    0.18
    _mpi
    0.18
    _MUX
    0.18
    侦
    0.18
    Activations Density 0.081%

    No Known Activations