© 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. 11867
    Prev
    Next
    INDEX
    Explanations

    SE, SCI, &P, Jones, Fortune, Fischer

    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
    utan
    -0.21
    çĶ¨åľ°
    -0.20
    .pen
    -0.20
    ilit
    -0.19
     hid
    -0.19
    æī¿æĭħ责任
    -0.18
    ylon
    -0.18
    ily
    -0.18
    _STA
    -0.18
    (Constructor
    -0.18
    POSITIVE LOGITS
    çĻ¾å¼º
    0.25
    iors
    0.21
    æłĩåĩĨ
    0.20
    ®
    0.20
    å²Į
    0.19
    ä½ĵç³»
    0.18
    ä¸ĩ象
    0.18
    åѦåłĤ
    0.18
    Anth
    0.17
    æŃ£åľ¨è¿Ľè¡Į
    0.17
    Activations Density 0.004%

    No Known Activations