© 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. 14731
    Prev
    Next
    INDEX
    Explanations

    general categories

    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
    å·§
    -0.26
    åѤ
    -0.20
    丧
    -0.20
    çݺ
    -0.19
    edition
    -0.19
    åīĶ
    -0.18
    anzeigen
    -0.18
    _CHARSET
    -0.18
     Twist
    -0.18
     ×ŀ׾×IJ
    -0.18
    POSITIVE LOGITS
    è½®å»ĵ
    0.30
    ç²Ĺ
    0.30
    æ¡Ĩæŀ¶
    0.29
    æ¦Ĥæĭ¬
    0.26
     vaguely
    0.26
    æ¦ĤåĨµ
    0.26
    大èĩ´
    0.26
     vague
    0.25
    åŁºè°ĥ
    0.25
    å®ıè§Ĥ
    0.24
    Activations Density 0.124%

    No Known Activations