© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14940
    Prev
    Next
    INDEX
    Explanations

    victim and crime victims

    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
    è¿ĻæĶ¯
    -0.21
    åī¿
    -0.20
     McMahon
    -0.20
    è¿Ļæī¹
    -0.20
    åıªè§ģ
    -0.19
    大家ä¸Ģèµ·
    -0.19
     Jaune
    -0.18
    Sa
    -0.18
    好æ¶Īæģ¯
    -0.18
    第ä¸Ģæī¹
    -0.18
    POSITIVE LOGITS
    æľªæĪIJå¹´
    0.22
    è£Ĩ
    0.19
    çĻ»è®°
    0.19
    为åħ¶
    0.19
    æĺ¯ä»ĸ
    0.19
    olynomial
    0.19
    å½ĵåľº
    0.19
    å½ĵæĻļ
    0.18
    ạ
    0.18
    oth
    0.18
    Activations Density 0.054%

    No Known Activations